Research map / 3D vision / Depth and stereo
Learning Single-Image Depth From Videos Using Quality Assessment Networks
Weifeng Chen, Shengyi Qian, Jia Deng
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 |
|---|---|---|---|
| Filter SfM video reconstructions with QANet to form YouTube3D | Hourglass depth network · DIW test | WHDR: 25.11% -> 19.01% | Improved |
| Add YouTube3D training data | Hourglass trained on NYU + DIW · DIW test | WHDR: 14.39% -> 13.50% | Improved |
| Add YouTube3D training data | EncDecResNet (our implementation) trained on ImageNet + ReDWeb + DIW · DIW test | WHDR: 12.03% -> 10.59% | Improved |
| Train on YouTube3D instead of DIW training data | Hourglass depth network · DIW test | WHDR: 22.14% -> 19.01% | Improved |
| Add QA_train to NYU training data | Hourglass depth network · DIW test | WHDR: 31.31% -> 31.22% | No clear effect |
| Add the 2D coordinate feature to QANet (ablation) | Full QANet · NYU Depth test | AUC: 80.53% -> 83.56% | Improved |
| Add the 2D coordinate feature to QANet (ablation) | Full QANet · FlyingThings3D test | AUC: 85.34% -> 89.02% | Improved |
| Add Sampson distance feature to QANet (ablation) | Full QANet · NYU Depth test | AUC: 83.20% -> 83.56% | Improved |
| Add Sampson distance feature to QANet (ablation) | Full QANet · FlyingThings3D test | AUC: 88.66% -> 89.02% | Improved |
| Add angle feature to QANet (ablation) | Full QANet · NYU Depth test | AUC: 82.09% -> 83.56% | Improved |
| Add angle feature to QANet (ablation) | Full QANet · FlyingThings3D test | AUC: 85.00% -> 89.02% | Improved |
| Add focal length feature to QANet (ablation) | Full QANet · NYU Depth test | AUC: 82.54% -> 83.56% | Improved |
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.
- MegaDepth — MegaDepth: Learning Single-View Depth Prediction From Internet Photos (CVPR 2018) · better on 1 of 1 shared result
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
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (CVPR 2025 · similarity 0.87)
- Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras (ICCV 2019 · similarity 0.87)
- Depth Any Video with Scalable Synthetic Data (ICLR 2025 · similarity 0.86)
- DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos (CVPR 2025 · similarity 0.85)
- From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos (NeurIPS 2024 · similarity 0.84)
- Align3R: Aligned Monocular Depth Estimation for Dynamic Videos (CVPR 2025 · similarity 0.84)
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.
