arXiv Computer Vision
A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
1d ago
SituHOI: Scalable Capture of Scene-Situated Full-Body Human-Object Interaction
arXiv:2610.23980v2 Announce Type: replace-cross Abstract: Modeling human-object interaction (HOI) in real environments requires jointly representing whole-body motion, manipulated objects, and scene...
arXiv Computer Vision
Oct 22
DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos
arXiv:2610.29936v1 Announce Type: new Abstract: Recovering metric world-space hand motion from egocentric video supports understanding human interactions and transferring them to embodied agents. Thr...
arXiv AI
Sep 30
FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
arXiv:2605.14854v3 Announce Type: replace-cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evide...
arXiv Computer Vision
Sep 23
WATCH: World-aware Allied Trajectory and pose reConstruction for Camera and Human
arXiv:2509.04600v2 Announce Type: replace Abstract: Reconstructing global human motion from monocular video is fundamental to VR, graphics, and robotics, yet remains ill-posed due to depth ambiguity,...
arXiv Computer Vision
Sep 30
World2Motion: Turning Video World Models into 3D Human Motion Generators
arXiv:2609.37004v1 Announce Type: new Abstract: We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt. While ex...
Hugging Face Trending Papers
3d ago
WorldProbe: When Video World Models Fall Apart under Long-Horizon Spatial Exploration
WorldProbe is a new diagnostic benchmark that tests video world models by letting a goal‑conditioned multimodal agent adapt camera actions online during generation, creating 164 test cases across four probing families. The benchmark evaluates 10 state‑of‑the‑art models over more than 1,600 rollouts, totaling roughly 800 minutes and horizons up to 180 seconds, revealing that while local visual and content quality can be maintained for longer, long‑range memory and evolution remain weak. The study highlights a gap between locally stable generation and persistent world consistency that existing short‑interaction benchmarks miss.