New AI models enhance image and video super-resolution with diffusion and efficient architectures
ByPulseAugur Editorial·
Summary by gemini-2.5-flash-lite
from 14 sources
Researchers are developing new methods for image and video super-resolution using advanced AI techniques. Several papers explore diffusion models for joint spatiotemporal super-resolution, enabling adaptation across different spatial and temporal scales. Other work focuses on efficient single-image super-resolution through quantization and teacher-guided training, as well as multi-frame super-resolution for specialized image sensors. Additionally, generative priors and ensemble methods are being leveraged to enhance detail recovery and bridge the gap between restoration and generation in real-world super-resolution tasks.
AI
Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal models are often designed for a single pair of super-resolution (SR) factors (upscaling spatial and t…
Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-oriented quantized SISR framework based on an extract-refine-u…
arXiv:2509.23980v2 Announce Type: replace Abstract: Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substanti…
arXiv:2604.24885v1 Announce Type: new Abstract: We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a nov…
arXiv:2604.25457v1 Announce Type: new Abstract: Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong…
Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text con…
arXiv:2604.24136v1 Announce Type: new Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR) but suffer from computational bottlenecks due to iterative sampling. Recent single-step distillation accelerates inference but faces a star…
arXiv cs.CV
TIER_1·Sangwook Baek, Vin Van Duong, Karam Park, Pilkyu Park·
arXiv:2604.23268v1 Announce Type: new Abstract: This paper introduces a novel multi frame super-resolution network (MFSR) for burst hexadeca Bayer pattern Contact Image Sensor (CIS) images, which includes demosaicing, denoising, multi-frame fusion, and super-resolution. Designing…
arXiv cs.CV
TIER_1·Dong Huo, Tristan Aumentado-Armstrong, Samrudhdhi B. Rangrej, Maitreya Suin, Angela Ning Ye, Zhiming Hu, Amanpreet Walia, Amirhossein Kazerouni, Konstantinos G. Derpanis, Iqbal Mohomed, Alex Levinshtein·
arXiv:2604.23508v1 Announce Type: new Abstract: Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) frames, relying on temporal redundancy and spatial coherence across the burst. Wh…
arXiv:2604.11564v2 Announce Type: replace Abstract: Single-image super-resolution has progressed from deep convolutional baselines to stronger Transformer and state-space architectures, yet the corresponding performance gains typically come with higher training cost, longer engin…
We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel resolution-agnostic 1D Transformer-based imag…
Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR) but suffer from computational bottlenecks due to iterative sampling. Recent single-step distillation accelerates inference but faces a stark perception-distortion trade-off due to rigid t…
We address the ambiguities in the super-resolution problem under translation. We demonstrate that combinations of low-resolution images at different scales can be used to make the super-resolution problem well posed. Such differences in scale can be achieved using sensors with di…
Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for real-world image super-resolution (Real-ISR). However, adapting VAR for ISR presents critical challenges. The next-scale predictio…
