Research map / Label-efficient and robust learning / Self-supervised and contrastive
Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation
Jingyuan Ma, Xiangyu Lei, Nan Liu, Xian Zhao, Shiliang Pu
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 full IC-MHA (intra + cross attention) and LNBT over the CMA + LBT baseline (ablation) | FSRE baseline · KITTI Eigen (R18) | SqRel: 0.730 -> 0.690 | Improved |
| add full IC-MHA and LNBT over baseline (ablation) | FSRE baseline · KITTI Eigen (R18) | AbsRel: 0.107 -> 0.104 | Improved |
| replace CMA with intra-task-only attention IC-MHA* (ablation) | FSRE baseline · KITTI Eigen (R18) | AbsRel: 0.107 -> 0.106 | Improved |
| replace CMA with IC-MHA(All) (intra + cross) (ablation) | FSRE baseline · KITTI Eigen (R18) | AbsRel: 0.107 -> 0.105 | Improved |
| replace CMA with IC-MHA(All) (ablation) | FSRE baseline · KITTI Eigen (R18) | SqRel: 0.730 -> 0.734 | No clear effect |
| add LBT and LCE-based semantic supervision with IC-MHA vs photometric only (ablation) | IC-MHA · KITTI Eigen (R18) | AbsRel: 0.110 -> 0.105 | Improved |
| add LNBT to IC-MHA with LCE and LBT (ablation) | IC-MHA · KITTI Eigen (R18) | SqRel: 0.734 -> 0.690 | Improved |
| add LNBT alone instead of LBT (ablation) | IC-MHA · KITTI Eigen (R18) | SqRel: 0.794 -> 0.727 | Improved |
| add LBT and LNBT together (ablation) | IC-MHA · KITTI Eigen (R18) | AbsRel: 0.105 -> 0.104 | Improved |
| use proposed IC-MHA for joint depth-segmentation | FSRE · KITTI 2015 segmentation | mIoU: 55.8 -> 56.3 | Improved |
| switch from ResNet-18 to ResNet-50 at 192x640 | Ours · KITTI Eigen | SqRel: 0.690 -> 0.656 | Improved |
| raise resolution to 320x1024 with ResNet-50 | Ours · KITTI Eigen | AbsRel: 0.102 -> 0.099 | Improved |
Closest papers by meaning
- Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth Estimation (ICCV 2021 · similarity 0.95)
- Semantically-Guided Representation Learning for Self-Supervised Monocular Depth (ICLR 2020 · similarity 0.92)
- Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation (ICCV 2021 · similarity 0.91)
- Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation (CVPR 2021 · similarity 0.91)
- Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation (ICCV 2025 · similarity 0.90)
- Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks (CVPR 2025 · 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.
