Research map / 3D vision / Depth and stereo
Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth Estimation
Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo
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 segmentation loss L_CE via shared encoder (ablation) | Monodepth2 · KITTI Eigen split | AbsRel: 0.114 -> 0.112 | Improved |
| add semantics-guided triplet loss (ablation) | Monodepth2 + L_CE · KITTI Eigen split | AbsRel: 0.112 -> 0.108 | Improved |
| add CMA module (ablation) | Monodepth2 + L_CE · KITTI Eigen split | AbsRel: 0.112 -> 0.107 | Improved |
| combine triplet loss and CMA module (ablation) | Monodepth2 + L_CE · KITTI Eigen split | AbsRel: 0.112 -> 0.105 | Improved |
| train with high-resolution images (ablation) | Full model · KITTI Eigen split | AbsRel: 0.105 -> 0.102 | Improved |
| use patch size K=5 instead of K=3 (ablation) | L_SGT · KITTI Eigen split | AbsRel: 0.109 -> 0.108 | Improved |
| use patch size K=5 instead of K=7 (ablation) | L_SGT · KITTI Eigen split | SqRel: 0.776 -> 0.755 | Improved |
| apply L_SGT to layer l=4 additionally (ablation) | L_SGT · KITTI Eigen split | SqRel: 0.755 -> 0.742 | Mixed |
| make CMA bidirectional (refine depth and segmentation) (ablation) | CMA module · KITTI Eigen split | AbsRel: 0.108 -> 0.107 | Improved |
| make CMA bidirectional versus segmentation-only target (ablation) | CMA module · KITTI Eigen split | AbsRel: 0.111 -> 0.107 | Improved |
| use four embeddings instead of one in CMA (ablation) | CMA module · KITTI Eigen split | SqRel: 0.762 -> 0.741 | Improved |
| use four embeddings instead of two in CMA (ablation) | CMA module · KITTI Eigen split | AbsRel: 0.107 -> 0.107 | No clear effect |
Closest papers by meaning
- Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation (ECCV 2022 · similarity 0.95)
- Semantically-Guided Representation Learning for Self-Supervised Monocular Depth (ICLR 2020 · similarity 0.93)
- Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation (ICCV 2021 · similarity 0.92)
- Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation (ICCV 2025 · similarity 0.92)
- Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks (CVPR 2025 · similarity 0.90)
- SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation (AAAI 2024 · similarity 0.89)
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.
