ECHO: Embodied Camera Observations of Human Object Carrying

arXiv:2610.10438 · cs.CV, cs.RO · Submitted 2026-10-07 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/hmthanh/3d-human-model

Terminology

• Benchmark — 19× in this paper · explained in 2 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 7× in this paper
• Embodied AI — 4× in this paper · explained in 2 episodes
• Conference on Robot Learning — 3× in this paper
• Grounding — 3× in this paper · explained in 3 episodes
• European Conference on Computer Vision — 2× in this paper
• Google Scanned Objects — 2× in this paper
• Amazon Berkeley Objects — 1× in this paper
• International Conference on Robotics and Automation — 1× in this paper
• Point Clouds — 1× in this paper · explained in 2 episodes

Sources

• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• AI2-THOR: An Interactive 3D Environment for Visual AI
• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• Rearrangement: A Challenge for Embodied AI

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