A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics
cs.CV
Submitted: 2026-10-14
Updated: 2026-10-15
Code: https://github.com/ultralytics/ultralytics
Project page: https://chien90190.github.io/worldhmr-fastcam-website
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Mask2Former for Video Instance Segmentation
- ViPE: Video Pose Engine for 3D Geometric Perception
- DROID-SLAM in the Wild
- Depth Anything 3: Recovering the Visual Space from Any Views
- SAM 2: Segment Anything in Images and Videos
- MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images
- BEDLAM2.0: Synthetic Humans and Cameras in Motion
- Multi-Human Mesh Recovery with Transformers
- Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
- SAM 3D Body: Robust Full-Body Human Mesh Recovery
- W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models