Research map / 3D vision / Depth and stereo
Monocular Relative Depth Perception With Web Stereo Data Supervision
Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo
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 |
|---|---|---|---|
| Train with ReDWeb pre-training followed by DIW fine-tuning rather than DIW training alone | Monocular relative depth model · DIW test | WHDR: 14.98% -> 11.37% | Improved |
| Train on ReDWeb with multiple point pairs rather than a single pair per image | Monocular relative depth model · DIW test | WHDR: 22.14% -> 14.33% | Improved |
| Train on diverse ReDWeb images rather than the indoor NYUDv2 data | Monocular relative depth model · DIW test | WHDR: 27.70% -> 14.33% | Improved |
| Fuse multi-scale features in the network (ablation) | Proposed ResNet-50 model · DIW validation | WHDR: 17.59% -> 15.74% | Improved |
| Use the improved ranking loss with hard-pair selection instead of ordinary ranking loss (ablation) | Proposed relative depth model · DIW validation | WHDR: 16.67% -> 15.74% | Improved |
| Use the improved ranking loss instead of ranking loss (ablation) | Relative depth model trained on the NYUDv2 subset · NYUDv2 | WKDR: 35.8% -> 33.7% | Improved |
| Increase the number of sampled point pairs per image (ablation) | Proposed relative depth model · DIW validation | WHDR | Improved |
| Increase the number of ReDWeb training images (ablation) | Proposed relative depth model · DIW validation | WHDR | Improved |
| Pre-train on ReDWeb before fine-tuning for metric depth estimation | ResNet-50 metric depth model · NYUDv2 | rel | Improved |
| Pre-train on ReDWeb before fine-tuning for semantic segmentation | ResNet-101 segmentation model · VOC 2012 | mIU: 69.67 -> 70.82 | Improved |
Closest papers by meaning
- Single-Image Depth Perception in the Wild (NeurIPS 2016 · similarity 0.90)
- Monocular Depth Estimation Using Relative Depth Maps (CVPR 2019 · similarity 0.89)
- Single View Stereo Matching (CVPR 2018 · similarity 0.88)
- DepthCues: Evaluating Monocular Depth Perception in Large Vision Models (CVPR 2025 · similarity 0.88)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.87)
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · 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.
