WATCH: World-aware Allied Trajectory and pose reConstruction for Camera and Human

arXiv:2509.04600 · cs.CV · Submitted 2025-09-04 · Read on arXiv

cs.CV

Submitted: 2025-09-04

Updated: 2026-09-22

Comments: Pacific Graphics 2026 camera-ready version. 10 pages main paper and 3 pages supplementary material; supplementary videos included

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 11× in this paper · explained in 3 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Transformer — 8× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 5× in this paper
• Loss Function — 5× in this paper · explained in 2 episodes
• Unified Framework — 5× in this paper · explained in 5 episodes
• Decoupling — 4× in this paper · explained in 2 episodes
• Human Pose and Shape Estimation — 4× in this paper
• World Model — 4× in this paper · explained in 7 episodes
• Entanglement — 3× in this paper · explained in 3 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Trace — 3× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 2× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Physical Constraints — 2× in this paper · explained in 7 episodes
• Point Clouds — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Temporal consistency — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Multi-modal Inputs — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Root Translation Error — 1× in this paper
• Standardized Metrics — 1× in this paper · explained in 3 episodes
• Temporal Correlations — 1× in this paper · explained in 2 episodes

Sources

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation
• HumanPlus: Humanoid Shadowing and Imitation from Humans
• Humans in 4D: Reconstructing and Tracking Humans with Transformers
• PACE: Human and Camera Motion Estimation from in-the-wild Videos
• GENMO: A GENeralist Model for Human MOtion
• Joint Optimization for 4D Human-Scene Reconstruction in the Wild
• DINOv2: Learning Robust Visual Features without Supervision
• CameraHMR: Aligning People with Perspective
• WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
• Deep Patch Visual Odometry
• VGGT: Visual Geometry Grounded Transformer
• DUSt3R: Geometric 3D Vision Made Easy
• PromptHMR: Promptable Human Mesh Recovery
• TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
• Decoupling Human and Camera Motion from Videos in the Wild
• WHAC: World-grounded Humans and Cameras
• HumanMM: Global Human Motion Recovery from Multi-shot Videos
• Synergistic Global-space Camera and Human Reconstruction from Videos

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