Research map / 3D vision / Depth and stereo
Unsupervised Learning of Depth and Ego-Motion From Video
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 explainability modeling to the depth-and-pose framework (ablation) | Ours · KITTI depth test | Abs Rel: 0.221 -> 0.208 | Helped |
| Add explainability modeling to the depth-and-pose framework (ablation) | Ours cap 50m · KITTI depth test, cap 50m | Abs Rel: 0.208 -> 0.201 | Helped |
| Pre-train on Cityscapes, then fine-tune on KITTI | Ours depth model · KITTI depth test | Abs Rel: 0.267 -> 0.198 | Helped |
| Use multiple views as input to the depth network instead of a single view (ablation) | Ours depth network · KITTI depth estimation | depth performance | No clear effect |
| Estimate pose from 5-frame snippets rather than the full driving sequence | ORB-SLAM · KITTI odometry Seq. 09 | ATE: 0.014 ± 0.008 -> 0.064 ± 0.141 | Hurt |
| Estimate pose from 5-frame snippets rather than the full driving sequence | ORB-SLAM · KITTI odometry Seq. 10 | ATE: 0.012 ± 0.011 -> 0.064 ± 0.130 | Hurt |
Closest papers by meaning
- Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric Constraints (CVPR 2018 · similarity 0.94)
- GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018 · similarity 0.91)
- Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos (AAAI 2019 · similarity 0.90)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.88)
- 3D Human Pose Perception from Egocentric Stereo Videos (CVPR 2024 · similarity 0.86)
- Seurat: From Moving Points to Depth (CVPR 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.