PulseAugur
EN
LIVE 09:27:06

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

By PulseAugur Editorial · [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

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 →

AI-generated summary · Google Gemini · from 5 sources. How we write summaries →

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

COVERAGE [5]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    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 English(EN) · 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 English(EN) · 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 English(EN) · 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 English(EN) · 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