Research map / 3D vision / Depth and stereo
Guiding Monocular Depth Estimation Using Depth-Attention Volume
Lam Huynh, Phong Nguyen-Ha, Jiri Matas, Esa Rahtu, Janne Heikkilä
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 the DAV module (ablation) | depth network · NYU-Depth-v2 | REL: 0.140 -> 0.108 | Improved |
| add the DAV module (ablation) | depth network · NYU-Depth-v2 | delta1: 0.827 -> 0.882 | Improved |
| increase planes from 0 to 3 (ablation) | DAV · NYU-Depth-v2 | REL: 0.116 -> 0.110 | Improved |
| increase planes from 3 to 5 (ablation) | DAV · NYU-Depth-v2 | REL: 0.110 -> 0.108 | Improved |
| increase planes from 5 to 7 (ablation) | DAV · NYU-Depth-v2 | REL: 0.108 -> 0.111 | Hurt |
| increase planes from 5 to 7 (ablation) | DAV · NYU-Depth-v2 | delta1: 0.882 -> 0.851 | Hurt |
| add the attention loss during training (ablation) | DAV · NYU-Depth-v2 | REL: 0.126 -> 0.108 | Improved |
| keep attention loss to the end instead of dropping it after convergence (ablation) | DAV · NYU-Depth-v2 | REL: 0.109 -> 0.108 | Improved |
| use cross-modulation in two embedding spaces instead of single embedding (ablation) | DAV module · NYU-Depth-v2 | REL: 0.115 -> 0.108 | Improved |
| add the DAV module (cross-dataset generalization) (ablation) | depth network · SUN-RGBD (trained on NYU) | REL: 0.254 -> 0.238 | Improved |
| use DAV model instead of Chen'19 on ScanNet | depth network · ScanNet official test | REL: 0.134 -> 0.118 | Improved |
Closest papers by meaning
- Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets (ECCV 2020 · similarity 0.91)
- Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss (ECCV 2018 · similarity 0.91)
- Trap Attention: Monocular Depth Estimation With Manual Traps (CVPR 2023 · similarity 0.89)
- Patch-Wise Attention Network for Monocular Depth Estimation (AAAI 2021 · similarity 0.89)
- Toward Practical Monocular Indoor Depth Estimation (CVPR 2022 · similarity 0.89)
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · 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.
