Home
News
Members
Publications
NVIDIA Research
Light
Dark
Automatic
Stan Birchfield
NVIDIA
Interests
3D Vision
Robotics
Latest
DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects
Partial-View Object View Synthesis via Filtering Inversion
HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions
Vicinity Vision Transformer
Affordance Diffusion: Synthesizing Hand-Object Interactions
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
One-Shot Neural Fields for 3D Object Understanding
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control
MegaPose: 6D Pose Estimation of Novel Objects via Render and Compare
6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark
Audio-Visual Segmentation
RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis
Displacement-Invariant Cost Computation for Efficient Stereo Matching
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation
Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image
Self-Supervised Real-to-Sim Scene Generation
Joint Space Control via Deep Reinforcement Learning
Multi-View Fusion for Multi-Level Robotic Scene Understanding
RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies
Deep Two-View Structure-from-Motion Revisited
DexYCB: A Benchmark for Capturing Hand Grasping of Objects
Fast Uncertainty Quantification for Deep Object Pose Estimation
Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
NViSII: A Scriptable Tool for Photorealistic Image Generation
Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views
Camera-to-robot pose estimation from a single image
DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
Toward Sim-to-Real Directional Semantic Grasping
Cite
×