CoDimRecon, an agentic framework detailed in arXiv paper 2609.36024v1, reconstructs editable, simulation-ready 3D scenes containing rigid, articulated, and deformable objects from multi-view RGB obser…
A mechanistic study of frozen foundation-model composition for generalized few-shot 3D segmentation found that retaining the full distribution of semantic alternatives before fusion reaches 34.87 harm…
Researchers introduced Self-Geometry, a test-time adaptation method that enforces explicit epipolar consistency to improve vision foundation models' depth and pose predictions without full retraining.…
Researchers introduced Ground3D-LMM, a unified model that processes point clouds and optional RGB images to enable 3D spatial conversations with point-grounded responses and metric numeric outputs. Th…