Research map / 3D vision / Depth and stereo
Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
Wencheng Han, Junbo Yin, Jianbing Shen
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 |
|---|---|---|---|
| add direction-aware module to DIFFNet (ablation) | DIFFNet · KITTI Eigen (M, 640x192) | RMSE: 4.483 -> 4.372 | Improved |
| add cumulative convolution to DIFFNet (ablation) | DIFFNet · KITTI Eigen (M, 640x192) | RMSE: 4.483 -> 4.380 | Improved |
| combine direction-aware module and cumulative convolution (ablation) | DIFFNet · KITTI Eigen (M, 640x192) | Abs Rel: 0.102 -> 0.099 | Improved |
| add cumulative convolution on delta<1.25 accuracy (ablation) | DIFFNet · KITTI Eigen (M, 640x192) | delta<1.25: 0.896 -> 0.897 | No clear effect |
| increase vertical input resolution (640x192 to 640x384) (ablation) | Monodepth2 · KITTI | Abs Rel: 0.115 -> 0.108 | Improved |
| increase horizontal input resolution (640x192 to 1280x192) (ablation) | Monodepth2 · KITTI | Abs Rel: 0.115 -> 0.118 | Hurt |
| replace DIFFNet backbone with DaCCN on Cityscapes | DaCCN vs prior methods · Cityscapes | Sq Rel: Abs Rel 0.119 -> 0.113; Sq Rel 1.290 -> 1.380 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BRNet — BRNet: Exploring Comprehensive Features for Monocular Depth Estimation (ECCV 2022) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume (CVPR 2020 · similarity 0.94)
- BRNet: Exploring Comprehensive Features for Monocular Depth Estimation (ECCV 2022 · similarity 0.93)
- Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019 · similarity 0.92)
- Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation (ICCV 2021 · similarity 0.91)
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth (CVPR 2021 · similarity 0.91)
- HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation (AAAI 2021 · similarity 0.91)
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.
