Latest

• FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
• 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