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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Replace stacked GRUs with a recurrent encoder-decoder (ablation) | MVS depth inference · WHU-3, same output resolution | MAE (m): 0.1882 -> 0.1574 | Improved |
| Replace stacked GRUs with a recurrent encoder-decoder (ablation) | MVS depth inference · WHU-5, same output resolution | MAE (m): 0.1505 -> 0.1379 | Improved |
| Replace stacked GRUs with a recurrent encoder-decoder (ablation) | MVS depth inference · München, same output resolution | MAE (m): 0.4264 -> 0.3677 | Improved |
| Train on WHU-3 rather than DTU | RED-Net · München | <3-interval (%): 63.04 -> 80.67 | Improved |
| Use RED-Net instead of SURE | München aerial reconstruction · München | <3-interval (%): 73.71 -> 80.67 | Improved |
| Use RED-Net instead of R-MVSNet | MVS depth inference · WHU-3 | MAE (m): 0.1882 -> 0.1120 | Improved |
| Use RED-Net instead of R-MVSNet | MVS depth inference · WHU-5 | MAE (m): 0.1505 -> 0.1041 | Improved |
| Use RED-Net instead of R-MVSNet | MVS depth inference · DTU | Overall (mm): 0.462 -> 0.391 | Improved |
Closest papers by meaning
- Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference (CVPR 2019 · similarity 0.89)
- Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement (CVPR 2020 · similarity 0.89)
- RRT-MVS: Recurrent Regularization Transformer for Multi-View Stereo (AAAI 2025 · similarity 0.88)
- AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis (CVPR 2025 · similarity 0.87)
- MVSAnywhere: Zero-Shot Multi-View Stereo (CVPR 2025 · similarity 0.86)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.86)
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.
