Research map / 3D vision / Depth and stereo
Open-World Stereo Video Matching with Deep RNN
Yiran Zhong, Hongdong Li, Yuchao Dai
Read the paperCheck 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 |
|---|---|---|---|
| add convolutional LSTM blocks (ablation) | OpenStereoNet · KITTI VO stereo (5 sequences) | Abs Rel: 0.066 -> 0.053 | Improved |
| add convolutional LSTM blocks (ablation) | OpenStereoNet · KITTI VO stereo (5 sequences) | Sq Rel: 1.580 -> 0.540 | Improved |
| add convolutional LSTM blocks (ablation) | OpenStereoNet · KITTI VO stereo (5 sequences) | RMSE: 5.332 -> 4.451 | Improved |
| add convolutional LSTM blocks (ablation) | OpenStereoNet · KITTI VO stereo (5 sequences) | D1_all: 5.089 -> 4.403 | Improved |
| add convolutional LSTM blocks (ablation) | OpenStereoNet · KITTI VO stereo (5 sequences) | delta<1.25: 0.957 -> 0.959 | Improved |
| add online backprop refinement and LSTMs to baseline network (ablation) | OpenStereoNet · KITTI VO training loss | training loss | Improved |
| use OpenStereoNet instead of DispNet | DispNet · KITTI VO stereo (5 sequences) | D1_all: 32.045 -> 4.403 | Improved |
| use OpenStereoNet instead of SPS-st | SPS-st · KITTI VO stereo (5 sequences) | D1_all: 4.970 -> 4.403 | Improved |
| change season and lighting from Spring to Night | OpenStereoNet · Synthia | MAE (pixels): 0.958 -> 1.2415 | Hurt |
Closest papers by meaning
- Practical Stereo Matching via Cascaded Recurrent Network With Adaptive Correlation (CVPR 2022 · similarity 0.92)
- Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains (CVPR 2018 · similarity 0.91)
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (JMLR 2016 · similarity 0.91)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.91)
- Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference (CVPR 2019 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.89)
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.
