Research map / Vision-language and multimodal / Robot action and navigation
DiNBV-Grasp: Real-Time Distance-Aware Two-Stage Next-Best-View for Robotic Grasping
Zilong Xie, Jingyu Gong, Xin Tan, Zhizhong Zhang, Yanyun Qu, Lizhuang Ma, Yuan Xie
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add distance-aware Stage II plug-in | ManipLLM · Simulation Test Seen | ASR (%): 56.00 -> 65.62 | Improved |
| add distance-aware Stage II plug-in | CrayonRobo · Simulation Test Unseen | ASR (%): 72.00 -> 79.67 | Improved |
| add distance-aware Stage II plug-in | Flowbot3D · Simulation Test Seen | ASR (%): 37.00 -> 45.16 | Improved |
| add distance-aware Stage II plug-in | RobMRAG · Simulation Test Unseen | ASR (%): 43.53 -> 51.76 | Improved |
| learned distance scorer instead of heuristic distance selection | ManipLLM · Simulation Test Seen | ASR (%): 61.58 -> 65.62 | Improved |
| select nearest observation instead of baseline distance | ManipLLM · Simulation Test Seen | ASR (%): 56.00 -> 41.37 | Hurt |
| add Stage II distance-aware refinement (ablation) | DiNBV-Grasp · Real-world scene c | SR: 2/10 -> 4/10 | Improved |
| add Stage II distance-aware refinement (ablation) | DiNBV-Grasp · Real-world scene e | SR: 3/10 -> 5/10 | Improved |
| add Stage II distance-aware refinement (ablation) | DiNBV-Grasp · Real-world scene a | SR: 6/10 -> 6/10 | No clear effect |
| add depth statistics and distance features to image-only scorer (ablation) | ResNet-18 scorer · Simulation Test Seen | ASR (%): 47.92 -> 49.58 | Improved |
| add object category prior to scorer (ablation) | ResNet-18 scorer · Simulation Test Seen | ASR (%): 49.58 -> 59.30 | Improved |
| add affordance features to scorer (ablation) | ResNet-18 scorer · Simulation Test Seen | avg frame time (ms): 59.30 -> 65.91 ASR, 27.97 -> 210.68 ms | Mixed |
Closest papers by meaning
- RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation (CVPR 2026 · similarity 0.88)
- Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges (NeurIPS 2025 · similarity 0.87)
- ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping (CVPR 2025 · similarity 0.87)
- Active Perception for Grasp Detection via Neural Graspness Field (NeurIPS 2024 · similarity 0.87)
- Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge (CVPR 2024 · similarity 0.86)
- Language-driven Grasp Detection (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
