iMED: A Multi-Endoscope Dataset for Surgical 3D Perception
cs.CV, cs.RO
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/surgical-vision/imed
Terminology
Sources
- 2018 Robotic Scene Segmentation Challenge
- Stereo Correspondence and Reconstruction of Endoscopic Data Challenge
- 2017 Robotic Instrument Segmentation Challenge
- SAM 3: Segment Anything with Concepts
- SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
- MITI: SLAM Benchmark for Laparoscopic Surgery
- DiffuEraser: A Diffusion Model for Video Inpainting
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- Benchmarking Image Similarity Metrics for Novel View Synthesis Applications
- EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
- Stereo Magnification: Learning View Synthesis using Multiplane Images
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs