Research map / Detection and segmentation / CNN features
SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation
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 category-aware depth estimation (ablation) | SDC-Depth · Cityscapes | RMSE: 7.203 -> 6.962 | Helped |
| Add instance-aware depth estimation (ablation) | SDC-Depth · Cityscapes | RMSE: 6.962 -> 6.958 | Helped |
| Disentangle canonical depth prediction from scale inference (ablation) | SDC-Depth · Cityscapes | RMSE: 6.958 -> 6.917 | Helped |
| Add category-aware depth estimation (ablation) | SDC-Depth · Cityscapes | δ < 1.25: 0.767 -> 0.794 | Helped |
| Add instance-aware depth estimation (ablation) | SDC-Depth · Cityscapes | δ < 1.25: 0.794 -> 0.797 | Helped |
| Disentangle canonical depth prediction from scale inference (ablation) | SDC-Depth · Cityscapes | δ < 1.25: 0.797 -> 0.801 | Helped |
| Train SDC-Depth with increasing amounts of COCO segmentation data (ablation) | SDC-Depth · DIW test | WHDR | Helped |
| Use semantic and instance segment-specific depth prediction instead of one direct depth prediction | SDC-Depth · DIW test | WHDR: 13.02% -> 11.21% | Helped |
Closest papers by meaning
- Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation (CVPR 2019 · similarity 0.92)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.90)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.88)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.88)
- Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks (CVPR 2025 · similarity 0.88)
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.