Research map / 3D vision / Depth and stereo
Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos
Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju
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 spatial correspondence module (ablation) | SC-GAN · KITTI | Abs Rel: 0.079 -> 0.063 | Improved |
| add spatial correspondence module (ablation) | SC-GAN · KITTI | RMSE: 2.301 -> 2.129 | Improved |
| add direction-based attention (ablation) | SC-GAN · KITTI | Abs Rel: 0.065 -> 0.063 | Improved |
| add direction-based attention (ablation) | SC-GAN · KITTI | RMSE: 2.182 -> 2.129 | Improved |
| add refinement subnetwork (ablation) | SC-GAN · KITTI | Abs Rel: 0.103 -> 0.063 | Improved |
| add refinement subnetwork (ablation) | SC-GAN · KITTI | RMSE: 3.354 -> 2.129 | Improved |
| add adversarial loss (ablation) | SC-GAN · KITTI | Abs Rel: 0.069 -> 0.063 | Improved |
| add adversarial loss (ablation) | SC-GAN · KITTI | RMSE: 2.653 -> 2.129 | Improved |
| use Chebyshev-type Smolyak level 7 instead of uniform sampling r=2 (ablation) | spatial correspondence module · KITTI | Abs Rel: 0.064 -> 0.063 | No clear effect |
| use Chebyshev-type Smolyak level 7 instead of uniform-type Smolyak level 7 (ablation) | spatial correspondence module · KITTI | Abs Rel: 0.066 -> 0.063 | Improved |
| raise Chebyshev Smolyak level from 5 to 8 (ablation) | spatial correspondence module · KITTI | Abs Rel: 0.074 -> 0.062 | Improved |
| raise uniform sampling rate from r=4 to r=2 (ablation) | spatial correspondence module · KITTI | Abs Rel: 0.071 -> 0.064 | Improved |
Closest papers by meaning
- Semi-Supervised Adversarial Monocular Depth Estimation (TPAMI 2019 · similarity 0.89)
- S³Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data (ECCV 2020 · similarity 0.88)
- Visualization of Convolutional Neural Networks for Monocular Depth Estimation (ICCV 2019 · similarity 0.87)
- Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network (ECCV 2018 · similarity 0.87)
- STViT: Improving Self-Supervised Multi-Camera Depth Estimation with Spatial-Temporal Context and Adversarial Geometry Regularization (Student Abstract) (AAAI 2024 · similarity 0.87)
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue (ECCV 2016 · similarity 0.87)
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.
