Research map / Architectures and efficiency / Attention and transformers
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
Read the paperCheck 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 Lite-Mono instead of MonoFormer | KITTI monocular training · KITTI Eigen split, M | Abs Rel: 0.108 -> 0.107 | Helped |
| Use Lite-Mono instead of R-MSFM6 | KITTI training without ImageNet pre-training · KITTI Eigen split, M† | Abs Rel: 0.126 -> 0.121 | Helped |
| Use Lite-Mono-8M instead of HR-Depth | KITTI at 1024×320 · KITTI Eigen split, M* | Abs Rel: 0.106 -> 0.097 | Helped |
| Use Lite-Mono-8M instead of MonoViT-tiny | KITTI monocular training · KITTI Eigen split, M | Abs Rel: 0.102 -> 0.101 | Helped |
| Use Lite-Mono rather than the strongest listed baseline | KITTI-trained model evaluated without fine-tuning · Make3D test | Abs Rel: 0.322 -> 0.305 | Helped |
| Add LGFI blocks (ablation) | Lite-Mono · KITTI Eigen split, 640×192 | Abs Rel: 0.111 -> 0.107 | Helped |
| Use dilated convolutions in CDC blocks (ablation) | Lite-Mono · KITTI Eigen split, 640×192 | Abs Rel: 0.112 -> 0.107 | Helped |
| Add pooled concatenations (ablation) | Lite-Mono · KITTI Eigen split, 640×192 | Abs Rel: 0.109 -> 0.107 | Helped |
| Add cross-stage connections (ablation) | Lite-Mono · KITTI Eigen split, 640×192 | Abs Rel: 0.108 -> 0.107 | Helped |
| Use the default dilation schedule rather than setting 2 (ablation) | Lite-Mono CDC blocks · KITTI Eigen split | Abs Rel: 0.110 -> 0.107 | Helped |
| Increase dilation rates in groups from 1, 2, 3 to 1, 2, 5 (ablation) | Lite-Mono CDC blocks · KITTI Eigen split | Abs Rel: 0.110 -> 0.108 | Helped |
| Use the default late-layer dilation schedule instead of very large late dilation rates (ablation) | Lite-Mono CDC blocks · KITTI Eigen split | Abs Rel: 0.110 -> 0.107 | Helped |
Closest papers by meaning
- Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation (AAAI 2023 · similarity 0.90)
- Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume (CVPR 2020 · similarity 0.89)
- Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks (CVPR 2025 · similarity 0.87)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.86)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.86)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.85)
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.