Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume
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 |
|---|---|---|---|
| Use self-attention and DDV with a ResNet101 encoder and dilated convolutions instead of the ResNet18 Monodepth2 baseline | Monodepth2 · KITTI 2015 Eigen split | Abs Rel: 0.115 -> 0.106 | Helped |
| Use the proposed self-supervised monocular method instead of Monodepth2 | Monodepth2 · Make3D | Abs Rel: 0.322 -> 0.297 | Helped |
| Add DDV (ablation) | Monodepth2 ResNet18 · KITTI 2015 Eigen split | Abs Rel: 0.115 -> 0.112 | Helped |
| Add self-attention (ablation) | Monodepth2 ResNet18 · KITTI 2015 Eigen split | Abs Rel: 0.115 -> 0.112 | Helped |
| Add self-attention and DDV (ablation) | Monodepth2 ResNet18 · KITTI 2015 Eigen split | Abs Rel: 0.115 -> 0.111 | Helped |
| Replace ResNet18 with ResNet101 and add dilated convolutions (ablation) | Monodepth2 · KITTI 2015 Eigen split | Abs Rel: 0.115 -> 0.110 | Helped |
| Add DDV (ablation) | ResNet101 with dilated convolutions · KITTI 2015 Eigen split | Abs Rel: 0.110 -> 0.110 | No clear effect |
| Add self-attention (ablation) | ResNet101 with dilated convolutions · KITTI 2015 Eigen split | Abs Rel: 0.110 -> 0.108 | Helped |
| Add DDV to the self-attention model (ablation) | ResNet101 with dilated convolutions and self-attention · KITTI 2015 Eigen split | Abs Rel: 0.108 -> 0.106 | Helped |
Closest papers by meaning
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth (CVPR 2021 · similarity 0.93)
- On the Uncertainty of Self-Supervised Monocular Depth Estimation (CVPR 2020 · similarity 0.93)
- Multi-Frame Self-Supervised Depth With Transformers (CVPR 2022 · similarity 0.92)
- Self-Supervised Learning of Depth Inference for Multi-View Stereo (CVPR 2021 · similarity 0.91)
- Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-Supervised Learning (AAAI 2022 · similarity 0.91)
- Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.90)
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.