Reproduce “FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Liangjing Shao, Wanhao Liu, Jinsong Lin, Zhiwei Fang, Hongliang Ren

FlowMoDE estimates depth from a single RGB image by using semantic features to guide coarse-to-fine flow matching, with two evaluations of a shared predictor at inference. Trained on 54K synthetic indoor frames, it improves KITTI AbsRel and δ₁ over PPD and reports lower mean point-cloud Chamfer distance than DepthMaster across NYUv2 and ETH3D. It does not lead every comparison.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.