Entities · Models
VGGT
8 articles tagged with this entity.
-
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
-
Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset
-
QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
-
WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation
-
Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
-
G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing
-
Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
-
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation