PulseAugur
LIVE 23:16:44
research · [73 sources] ·
0
research

3D Gaussian Splatting advances in compression, aesthetics, and autonomous driving

Recent research explores advancements in 3D Gaussian Splatting (3DGS), a technique for real-time photorealistic novel-view synthesis. New methods like GETA-3DGS focus on efficient compression through joint pruning and quantization, achieving significant storage reduction. Other work, such as EnerGS, introduces soft geometric guidance to improve reconstruction quality in challenging outdoor scenarios with incomplete data. Additionally, FreeTimeGS++ enhances dynamic scene reconstruction by analyzing and optimizing temporal partitioning and spatiotemporal consistency, while WildSplatter enables feed-forward 3DGS from unconstrained images with appearance control. AI

Summary written by gemini-2.5-flash-lite from 73 sources. How we write summaries →

IMPACT These advancements in 3D Gaussian Splatting are improving efficiency, handling dynamic scenes, and enabling new applications in areas like autonomous driving and AR/VR.

RANK_REASON Multiple arXiv papers present novel research and techniques related to 3D Gaussian Splatting.

Read on Hugging Face Blog →

COVERAGE [73]

  1. Hugging Face Blog TIER_1 ·

    Introduction to 3D Gaussian Splatting

  2. Hugging Face Daily Papers TIER_1 ·

    Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

    As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emp…

  3. arXiv cs.LG TIER_1 · Baobing Zhang, Wanxin Sui ·

    GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting

    arXiv:2605.02086v1 Announce Type: new Abstract: 3D Gaussian splatting (3DGS) is a state-of-the-art representation for real-time photorealistic novel-view synthesis, yet a single high-fidelity scene typically occupies hundreds of megabytes to several gigabytes, exceeding the budge…

  4. Hugging Face Daily Papers TIER_1 ·

    From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving

    The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect to the list of rare but still possible safety-re…

  5. Hugging Face Daily Papers TIER_1 ·

    EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors

    3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or …

  6. Hugging Face Daily Papers TIER_1 ·

    WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images

    We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requ…

  7. arXiv cs.CV TIER_1 · Gim Hee Lee ·

    Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

    Surface reconstruction with differentiable rendering has achieved impressive performance in recent years, yet the pervasive photometric ambiguities have strictly bottlenecked existing approaches. This paper presents AmbiSuR, a framework that explores an intrinsic solution upon Ga…

  8. arXiv cs.CV TIER_1 · Suryansh Kumar ·

    3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark

    Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across time. In this paper, we argue that, in a s…

  9. arXiv cs.CV TIER_1 · Xiaopeng Fan ·

    PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

    Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existing methods mainly focus on designing increasingly sophisticated dropout strategies, while they overlook the resulting inconsiste…

  10. arXiv cs.CV TIER_1 · Chi-Keung Tang ·

    TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering

    Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement between near-field reflections from the surrounding environment on the transmissive surface, and the transmitted content of the scen…

  11. arXiv cs.CV TIER_1 · Mae Younes, Adnane Boukhayma ·

    3DSS: 3D Surface Splatting for Inverse Rendering

    arXiv:2605.05876v1 Announce Type: cross Abstract: We present 3D Surface Splatting (3DSS), the first differentiable surface splatting renderer for physically-based inverse rendering from multi-view images. Our central insight is that the surface separation problem at the heart of …

  12. arXiv cs.CV TIER_1 · Junmyeong Lee, Hoseung Choi, Yoonwoo Jeong, Minsu Cho ·

    RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos

    arXiv:2412.03077v2 Announce Type: replace Abstract: 4D reconstruction from casually captured monocular videos is challenging due to inherent ambiguity in reconstructing dynamic 3D geometry. To address this challenge, we introduce Robust Dynamic Gaussian Splatting (RoDyGS), a meth…

  13. arXiv cs.CV TIER_1 · Chuanzhi Xu, Boyu Wei, Haoxian Zhou, Xuanhua Yin, Zihan Deng, Haodong Chen, Qiang Qu, Weidong Cai ·

    Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

    arXiv:2605.05155v1 Announce Type: new Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existin…

  14. arXiv cs.CV TIER_1 · Xinze Li, Bohan Yang, Pengxu Chen, Yiyuan Wang, Hongcheng Luo, Wentao Cheng, Weifeng Su ·

    QuadBox: Accelerating 3D Gaussian Splatting with Geometry-Aware Boxes

    arXiv:2605.04844v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using differentiable Gaussian primitives. However, efficiently computing precise Gaus…

  15. arXiv cs.CV TIER_1 · Binh Long Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes, Peyman Moghadam ·

    Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting

    arXiv:2605.04506v1 Announce Type: new Abstract: We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association,…

  16. arXiv cs.CV TIER_1 · Jun-Jee Chao, Volkan Isler ·

    SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting

    arXiv:2601.00285v2 Announce Type: replace Abstract: Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on mul…

  17. arXiv cs.CV TIER_1 · Xuezhen Wang, Li Ma, Yulin Shen, Zeyu Wang, Pedro V. Sander ·

    RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting

    arXiv:2603.13783v2 Announce Type: replace Abstract: Temporal retiming, the ability to reconstruct and render dynamic scenes at arbitrary timestamps, is crucial for applications such as slow-motion playback, temporal editing, and post-production. However, most existing 4D Gaussian…

  18. arXiv cs.CV TIER_1 · Weidong Cai ·

    Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

    As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emp…

  19. arXiv cs.CV TIER_1 · Weifeng Su ·

    QuadBox: Accelerating 3D Gaussian Splatting with Geometry-Aware Boxes

    3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using differentiable Gaussian primitives. However, efficiently computing precise Gaussian-tile intersections remains a critical task …

  20. arXiv cs.CV TIER_1 · Peyman Moghadam ·

    Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting

    We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association, which undermines cross-view consistency, lacks …

  21. arXiv cs.CV TIER_1 · Lucas Yunkyu Lee, Soonho Kim, Youngwook Kim, Sangmin Kim, Jaesik Park ·

    FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles

    arXiv:2605.03337v1 Announce Type: new Abstract: The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a sys…

  22. arXiv cs.CV TIER_1 · Qian Wang, Zhihao Zhan, Jialei He, Zhituo Tu, Jie Yuan ·

    High-Quality Spatial Reconstruction and Orthoimage Generation Using Efficient 2D Gaussian Splatting

    arXiv:2503.19703v3 Announce Type: replace Abstract: Highly accurate geometric precision and dense image features characterize True Digital Orthophoto Maps (TDOMs), which are in great demand for applications such as urban planning, infrastructure management, and environmental moni…

  23. arXiv cs.CV TIER_1 · Shima Salehi, Atharva Agashe, Andrew J. McFarland, Joshua Peeples ·

    LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction

    arXiv:2601.17185v2 Announce Type: replace Abstract: We propose a new method for few-shot 3D reconstruction that integrates global and local frequency regularization to stabilize geometry and preserve fine details under sparse-view conditions, addressing a key limitation of existi…

  24. arXiv cs.CV TIER_1 · Peizhen Zheng, Dongjing Jiang, Qingchong Jiao, Redouane EL Bouchtaoui, Flynnwell Jianfei Zhang ·

    3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction

    arXiv:2503.12001v4 Announce Type: replace Abstract: The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle wi…

  25. arXiv cs.CV TIER_1 · Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura ·

    SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

    arXiv:2411.18966v2 Announce Type: replace Abstract: Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to repre…

  26. arXiv cs.CV TIER_1 · Jiajun Huang, Shuolin Xu, Hongchuan Yu, Tong-Yee Lee ·

    GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting

    arXiv:2405.15491v4 Announce Type: replace Abstract: We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS). Our approach bridges cage-based deformation and 3DGS by using a proxy point-cloud representation. This point cloud is generated…

  27. arXiv cs.CV TIER_1 · Ali Nouri, Yifei Zhang, Yifan Zhang, Tayssir Bouraffa, Zhennan Fei, Zijian Han, H{\aa}kan Sivencrona, Anders Heyden ·

    From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving

    arXiv:2605.01995v1 Announce Type: new Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect …

  28. arXiv cs.CV TIER_1 · Zhaoyang Li, Zhichao You, Tianrui Li ·

    SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion

    arXiv:2605.01466v1 Announce Type: new Abstract: Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs …

  29. arXiv cs.CV TIER_1 · Jaesik Park ·

    FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles

    The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a systematic understanding of the underlying principl…

  30. arXiv cs.CV TIER_1 · Suyi Chen, Haibin Ling ·

    CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction

    arXiv:2508.04929v5 Announce Type: replace-cross Abstract: As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution. The core computational task in single-particle cr…

  31. arXiv cs.CV TIER_1 · Kaixuan Zhang, Minxian Li, Mingwu Ren, Jiankang Deng, Xiatian Zhu ·

    High Dynamic Range 3D Gaussian Splatting via Luminance-Chromaticity Decomposition

    arXiv:2511.12895v3 Announce Type: replace Abstract: High Dynamic Range (HDR) 3D reconstruction is pivotal for professional content creation in filmmaking and virtual production. Existing methods typically rely on multi-exposure Low Dynamic Range (LDR) supervision to constrain the…

  32. arXiv cs.CV TIER_1 · Qianfan Shen, Ningxiao Tao, Qiyu Dai, Tianle Chen, Minghan Qin, Yongjie Zhang, Mengyu Chu, Wenzheng Chen, Baoquan Chen ·

    FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting

    arXiv:2605.00177v1 Announce Type: cross Abstract: We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, …

  33. arXiv cs.CV TIER_1 · Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha, Mirela Ostrek, Justus Thies ·

    2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction

    arXiv:2605.00569v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To …

  34. arXiv cs.CV TIER_1 · Sungjun Cho ·

    Two-View Accumulation as the Primary Training Lever for Hybrid-Capture Gaussian Splatting: A Variance-Decomposition View of When Gradient Surgery Helps

    arXiv:2605.00052v1 Announce Type: new Abstract: Hybrid-capture novel view synthesis combines images at substantially different camera distances (e.g., aerial drone and ground-level views). Standard 3D Gaussian Splatting (3DGS), trained for 30K iterations with one rendered view pe…

  35. arXiv cs.CV TIER_1 · Zhenhua Ning, Xin Li, Jun Yu, Guangming Lu, Yaowei Wang, Wenjie Pei ·

    Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting

    arXiv:2605.00408v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, su…

  36. arXiv cs.CV TIER_1 · Justus Thies ·

    2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction

    3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address this, 2D Gaussian Splatting (2DGS) was p…

  37. arXiv cs.CV TIER_1 · Wenjie Pei ·

    Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting

    While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to ad…

  38. arXiv cs.CV TIER_1 · Andrea Dunn Beltran, Daniel Rho, Aarav Mehta, Xinqi Xiong, Ra\'ul San Jos\'e Est\'epar, Ron Alterovitz, Marc Niethammer, Roni Sengupta ·

    Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy

    arXiv:2604.28179v1 Announce Type: new Abstract: Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is …

  39. arXiv cs.CV TIER_1 · Wongi Park, Jordan A. James, Myeongseok Nam, Minjae Lee, Soomok Lee, Sang-Hyun Lee, William J. Beksi ·

    Sparse-View 3D Gaussian Splatting in the Wild

    arXiv:2604.27422v1 Announce Type: new Abstract: We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images witho…

  40. arXiv cs.CV TIER_1 · Jian Lin, Jiancheng Fang, Shaoyu Wang, Changan Lai, Yikun Zhang, Yang Chen, Qiegen Liu ·

    Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstruction

    arXiv:2604.27552v1 Announce Type: new Abstract: While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-…

  41. arXiv cs.CV TIER_1 · Linjie Lyu, Ayush Tewari, Jianchun Chen, Thomas Leimk\"uhler, Christian Theobalt ·

    Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

    arXiv:2604.28016v1 Announce Type: new Abstract: 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between ge…

  42. arXiv cs.CV TIER_1 · Boyang Tony Yu, Yanlin Jin, Yun He, Akshat Dave, Ravi Ramamoorthi, Guha Balakrishnan ·

    TranSplat: Instant Object Relighting in Gaussian Splatting via Spherical Harmonic Radiance Transfer

    arXiv:2503.22676v5 Announce Type: replace Abstract: We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we propose a BRDF-free radiance transfer strategy tha…

  43. arXiv cs.CV TIER_1 · Baoquan Chen ·

    FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting

    We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, expert-tuned parameters, and labor-intensive workf…

  44. arXiv cs.CV TIER_1 · Roni Sengupta ·

    Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy

    Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is mitigated through breath-hold protocols, which a…

  45. arXiv cs.CV TIER_1 · Christian Theobalt ·

    Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

    3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, oft…

  46. arXiv cs.CV TIER_1 · Qiegen Liu ·

    Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstruction

    While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view conditions, leading to over-smoothing and a…

  47. arXiv cs.CV TIER_1 · William J. Beksi ·

    Sparse-View 3D Gaussian Splatting in the Wild

    We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained …

  48. arXiv cs.CV TIER_1 · Shuzhao Xie, Junchen Ge, Weixiang Zhang, Jiahang Liu, Chen Tang, Yunpeng Bai, Shijia Ge, Jingyan Jiang, Yuzhi Huang, Fengnian Yang, Cong Zhang, Xiaoyi Fan, Zhi Wang ·

    MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching

    arXiv:2604.26799v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupl…

  49. arXiv cs.CV TIER_1 · Ahmad Droby ·

    Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting

    arXiv:2604.16747v2 Announce Type: replace Abstract: Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes…

  50. arXiv cs.CV TIER_1 · Rui Song, Tianhui Cai, Markus Gross, Yun Zhang, Walter Zimmer, Zhiyu Huang, Olaf Wysocki, Jiaqi Ma ·

    EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors

    arXiv:2604.26238v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as L…

  51. arXiv cs.CV TIER_1 · Zhi Wang ·

    MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching

    3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupled hyperparameters across pruning, transformatio…

  52. arXiv cs.CV TIER_1 · Yuezhe Yang, Qingqing Ruan, Wenjie Cai, Yudang Dong, Dexin Yang, Xingbo Dong, Zhe Jin, Yong Dai ·

    UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis

    arXiv:2511.07743v3 Announce Type: replace Abstract: Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view poses challenges for novel view synthesis. We present UltraGS, a real-time framework that adapts Gaussian Splatting to senso…

  53. arXiv cs.CV TIER_1 · Jingi Kim, Wonjun Kim ·

    Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency

    arXiv:2604.25466v1 Announce Type: new Abstract: Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural represe…

  54. arXiv cs.CV TIER_1 · Jiaqi Ma ·

    EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors

    3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or …

  55. arXiv cs.CV TIER_1 · Wonjun Kim ·

    Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency

    Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Al…

  56. arXiv cs.CV TIER_1 · Jingjing Jiang ·

    GS-DOT: Gaussian splatting-based image reconstruction for diffuse optical tomography

    arXiv:2604.23675v1 Announce Type: cross Abstract: This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficients are represented as a spars…

  57. arXiv cs.CV TIER_1 · Daniel Wang, Patrick Rim, Tian Tian, Dong Lao, Alex Wong, Ganesh Sundaramoorthi ·

    ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting

    arXiv:2506.05480v4 Announce Type: replace-cross Abstract: We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enable future extrapolation of dynamic 3D scenes. Unlike existing dynamic scene recon…

  58. arXiv cs.CV TIER_1 · Di Wu, Liu Liu, Xueyu Yuan, Wenxiao Chen, Lijun Yue, Liuzhu Chen, Yiming Tang, Meng Wang ·

    SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting

    arXiv:2511.17092v4 Announce Type: replace Abstract: Articulated objects are ubiquitous in daily environments, and their 3D reconstruction holds great significance across various fields. However, existing articulated object reconstruction methods typically require costly inputs su…

  59. arXiv cs.CV TIER_1 · YuHao Yin, Zongji Wang, Yuanben Zhang, Biqing Li, Jiesong Bai, Junyi Liu ·

    Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling

    arXiv:2604.24053v1 Announce Type: new Abstract: Full 360$^\circ$ novel view synthesis under low-light conditions remains challenging. Insufficient illumination, noise amplification, and view-dependent photometric inconsistencies prevent existing methods from jointly preserving ge…

  60. arXiv cs.CV TIER_1 · Jan Warchocki, Xi Wang, Jonas Kulhanek, Jan van Gemert ·

    Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction

    arXiv:2604.23803v1 Announce Type: new Abstract: Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive technologies. However, rapid camera motion and complex scene dynamics pose major ch…

  61. arXiv cs.CV TIER_1 · Shaohua Liu, Ning Gao, Zuoya Gu, Hongkun Dou, Yue Deng, Hongjue Li ·

    Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction

    arXiv:2604.23551v1 Announce Type: new Abstract: Reconstructing realistic underwater scenes from underwater video remains a meaningful yet challenging task in the multimedia domain. The inherent spatiotemporal degradations in underwater imaging, including caustics, flickering, att…

  62. arXiv cs.CV TIER_1 · Junyi Liu ·

    Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling

    Full 360$^\circ$ novel view synthesis under low-light conditions remains challenging. Insufficient illumination, noise amplification, and view-dependent photometric inconsistencies prevent existing methods from jointly preserving geometric consistency and photorealism. Unsupervis…

  63. arXiv cs.CV TIER_1 · Jinrang Jia, Zhenjia Li, Yifeng Shi ·

    You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes

    arXiv:2604.21400v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has revolutionized neural rendering, yet existing methods remain predominantly research prototypes ill-suited for production-level deployment. We identify a critical "Industry-Academia Gap" hindering…

  64. arXiv cs.CV TIER_1 · Yangming Zhang, Jian Xu, Chaojian Li, Kunxiong Zhu, Wei Niu, Gagan Agrawal, Yang Katie Zhao, Jian Wang, Yingyan Celine Lin, Miao Yin ·

    Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training

    arXiv:2604.20046v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis with high-quality rendering through continuous aggregations of millions of 3D Gaussian primitives. However, it suffers from a substantial memory footprint, par…

  65. arXiv cs.CV TIER_1 · Zaiyan Yang, Xinpeng Liu, Heng Guo, Jinglei Shi, Zhanyu Ma, Fumio Okura ·

    NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting

    arXiv:2604.22439v1 Announce Type: new Abstract: We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features ex…

  66. arXiv cs.CV TIER_1 · Feiyu An, Yufei Deng, Zihui Zhang, Rong Xiao ·

    EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting

    arXiv:2604.22183v1 Announce Type: new Abstract: Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual arti…

  67. arXiv cs.CV TIER_1 · David Recasens, Robert Maier, Aljaz Bozic, Stephane Grabli, Javier Civera, Tony Tung, Edmond Boyer ·

    PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

    arXiv:2604.22129v1 Announce Type: new Abstract: Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread a…

  68. arXiv cs.CV TIER_1 · Fumio Okura ·

    NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting

    We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features extracted from vision foundation models suffer fro…

  69. arXiv cs.CV TIER_1 · Rong Xiao ·

    EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting

    Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual artifacts and blurry texture details due to misleadi…

  70. arXiv cs.CV TIER_1 · Edmond Boyer ·

    PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

    Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread and shapes, such as 2D Gaussian Splatting, have s…

  71. arXiv cs.CV TIER_1 · Yisong Chen ·

    DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures

    While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate multi-view consistency. Existing methods face a circular dependency: accurate transient detection req…

  72. arXiv cs.CV TIER_1 · Yifeng Shi ·

    You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes

    3D Gaussian Splatting (3DGS) has revolutionized neural rendering, yet existing methods remain predominantly research prototypes ill-suited for production-level deployment. We identify a critical "Industry-Academia Gap" hindering real-world application: unpredictable resource cons…

  73. arXiv cs.CV TIER_1 · Yasuhiro Mukaigawa ·

    WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images

    We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requ…