Martine: Benchmarking Multi-View 3D Surface Reconstruction Across Viewpoint Coverage, Resolution, and Lighting
cs.CV
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/martine-benchmark/martine-dataset
Project page: https://martine-benchmark.github.io
Terminology
Sources
- LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo
- EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
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