PulseAugur
LIVE 09:44:09
research · [5 sources] ·
0
research

New AI models InterMesh and Anny-Fit advance 3D human pose and shape recovery

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 5 sources

Researchers have developed InterMesh, a new framework for multi-person human mesh recovery that explicitly incorporates human-environment interaction information. This approach enhances pose and shape estimation by enriching query representations with structured interaction semantics, leading to significant improvements on benchmark datasets. Separately, Anny-Fit is introduced as a multi-person optimization framework for all-age 3D human mesh recovery, which jointly optimizes individuals and leverages various forms of expert knowledge to improve accuracy and coherence. AI

Summary written by gemini-2.5-flash-lite from 5 sources. How we write summaries →

IMPACT These advancements in human mesh recovery could improve applications in robotics, augmented reality, and animation by enabling more accurate and context-aware 3D human modeling.

RANK_REASON Two distinct research papers are presented on arXiv detailing novel methods for 3D human mesh recovery.

Read on arXiv cs.CV →

COVERAGE [5]

  1. Hugging Face Daily Papers TIER_1 ·

    InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

    Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relationships through self-attention across all human queries. However, these approaches model interactions…

  2. arXiv cs.CV TIER_1 · Kaili Zheng, Kaiwen Wang, Xun Zhu, Chenyi Guo, Ji Wu ·

    InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

    arXiv:2605.04554v1 Announce Type: new Abstract: Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relationships through self-attention across all human queri…

  3. arXiv cs.CV TIER_1 · Laura Bravo-S\'anchez, Matthieu Armando, Romain Br\'egier, Gr\'egory Rogez, Serena Yeung-Levy, Fabien Baradel ·

    Anny-Fit: All-Age Human Mesh Recovery

    arXiv:2605.04728v1 Announce Type: new Abstract: Recovering 3D human pose and shape from a single image remains a cornerstone of human-centric vision, yet most methods assume adult subjects and optimize each person independently. These assumptions fail in real-world, all-age scene…

  4. arXiv cs.CV TIER_1 · Fabien Baradel ·

    Anny-Fit: All-Age Human Mesh Recovery

    Recovering 3D human pose and shape from a single image remains a cornerstone of human-centric vision, yet most methods assume adult subjects and optimize each person independently. These assumptions fail in real-world, all-age scenes, where body proportions and depth must be reso…

  5. arXiv cs.CV TIER_1 · Ji Wu ·

    InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

    Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relationships through self-attention across all human queries. However, these approaches model interactions…

RELATED ENTITIES

RELATED TOPICS