RecGen achieves state-of-the-art 3D multi-object scene reconstruction from sparse RGB-D views by combining compositional synthetic scene generation with strong 3D shape priors, outperforming SAM3D by 30%+ in shape quality and pose accuracy while using 80% fewer meshes.
GraspSplats: Efficient Manipulation with 3D Feature Splatting
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.
The viewpoint-agnostic grasp pipeline using VLM and partial observation handling achieves 90% success (9/10 trials) in cluttered tabletop scenarios on a real quadruped robot, outperforming a view-dependent baseline at 30% (3/10) through open-vocabulary detection, point cloud completion, and safety-0
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
citing papers explorer
-
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
RecGen achieves state-of-the-art 3D multi-object scene reconstruction from sparse RGB-D views by combining compositional synthetic scene generation with strong 3D shape priors, outperforming SAM3D by 30%+ in shape quality and pose accuracy while using 80% fewer meshes.
-
GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.
-
Viewpoint-Agnostic Grasp Pipeline using VLM and Partial Observations
The viewpoint-agnostic grasp pipeline using VLM and partial observation handling achieves 90% success (9/10 trials) in cluttered tabletop scenarios on a real quadruped robot, outperforming a view-dependent baseline at 30% (3/10) through open-vocabulary detection, point cloud completion, and safety-0
-
A Survey on 3D Gaussian Splatting
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.