AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-View Stereo Reconstruction From an Open Aerial Dataset

Jin Liu, Shunping Ji

CVPR 2020 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 115 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Replace stacked GRUs with a recurrent encoder-decoder (ablation)MVS depth inference · WHU-3, same output resolutionMAE (m): 0.1882 -> 0.1574Improved
Replace stacked GRUs with a recurrent encoder-decoder (ablation)MVS depth inference · WHU-5, same output resolutionMAE (m): 0.1505 -> 0.1379Improved
Replace stacked GRUs with a recurrent encoder-decoder (ablation)MVS depth inference · München, same output resolutionMAE (m): 0.4264 -> 0.3677Improved
Train on WHU-3 rather than DTURED-Net · München<3-interval (%): 63.04 -> 80.67Improved
Use RED-Net instead of SUREMünchen aerial reconstruction · München<3-interval (%): 73.71 -> 80.67Improved
Use RED-Net instead of R-MVSNetMVS depth inference · WHU-3MAE (m): 0.1882 -> 0.1120Improved
Use RED-Net instead of R-MVSNetMVS depth inference · WHU-5MAE (m): 0.1505 -> 0.1041Improved
Use RED-Net instead of R-MVSNetMVS depth inference · DTUOverall (mm): 0.462 -> 0.391Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy