VGGT-Segmentor achieves new SOTA cross-view segmentation on Ego-Exo4D (67.7% Ego-to-Exo, 68.0% Exo-to-Ego IoU) via geometry-enhanced features, a three-stage segmentation head, and correspondence-free pretraining.
Structure- from-motion revisited
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
FACT-GS allocates higher texture sampling density to high-frequency areas in 2D Gaussian Splatting through a learnable deformation field, recovering sharper details at the same parameter budget.
citing papers explorer
-
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
VGGT-Segmentor achieves new SOTA cross-view segmentation on Ego-Exo4D (67.7% Ego-to-Exo, 68.0% Exo-to-Ego IoU) via geometry-enhanced features, a three-stage segmentation head, and correspondence-free pretraining.
-
SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
-
FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting
FACT-GS allocates higher texture sampling density to high-frequency areas in 2D Gaussian Splatting through a learnable deformation field, recovering sharper details at the same parameter budget.