Research map / 3D vision / Depth and stereo
PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in Endoscopy
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces PolypSense3D, a multi-source benchmark dataset of over 43,000 frames for depth-aware polyp size measurement in endoscopy.
Problem
Polyp size measurement during endoscopy is subjective and existing datasets lack integrated 2D appearance, 3D structure, and real-world size information.
Approach
A multi-source dataset combining virtual simulation, physical phantom and other sources, integrating 2D appearance, 3D depth and ground-truth size for depth-aware polyp sizing.
Key results
- PolypSense3D integrates over 43,000 frames from virtual simulations, physical models and other sources.
Closest papers by meaning
- Unsupervised Photometric-Consistent Depth Estimation from Endoscopic Monocular Video (AAAI 2025 · similarity 0.84)
- Polyper: Boundary Sensitive Polyp Segmentation (AAAI 2024 · similarity 0.84)
- VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging (CVPR 2025 · similarity 0.84)
- An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · similarity 0.82)
- EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis (NeurIPS 2025 · similarity 0.82)
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations (NeurIPS 2025 · similarity 0.82)
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.