COVScene is a pose-free framework that lifts semantic Gaussians into a volumetric occupancy field during training to jointly support novel view synthesis, open-vocabulary segmentation, and semantic occupancy prediction.
Vggt: Visual geometry grounded transformer
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.
citing papers explorer
-
Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images
COVScene is a pose-free framework that lifts semantic Gaussians into a volumetric occupancy field during training to jointly support novel view synthesis, open-vocabulary segmentation, and semantic occupancy prediction.
-
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.
-
Towards a Multi-Embodied Grasping Agent
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.