Research map / 3D vision / Depth and stereo
From Depth What Can You See? Depth Completion via Auxiliary Image Reconstruction
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 auxiliary image reconstruction during training with shared features | depth-only depth completion · KITTI depth completion test | RMSE: 901.43 vs 922.93 | Helped |
| use sparse-depth-only auxiliary image reconstruction instead of an RGB image input at test time | depth completion · NYUv2 test | RMSE: 0.125 vs 0.117; 0.125 vs 0.115 | Mixed |
| add image reconstruction without feature sharing (ablation) | B depth-features-only baseline · KITTI depth completion validation | RMSE: 1267.01 -> 1103.85 | Helped |
| add image reconstruction without feature sharing (ablation) | B depth-features-only baseline · KITTI depth completion validation | MAE: 322.32 -> 301.64 | Helped |
| add feature sharing between depth and image modules (ablation) | B + I · KITTI depth completion validation | RMSE: 1103.85 -> 914.65 | Helped |
| add feature sharing between depth and image modules (ablation) | B + I · KITTI depth completion validation | MAE: 301.64 -> 297.38 | Helped |
| replace ℓ2 loss with ℓ1 loss (ablation) | proposed depth completion model · KITTI depth completion test | MAE: 292.36 -> 231.37 | Helped |
| replace ℓ2 loss with ℓ1 loss (ablation) | proposed depth completion model · KITTI depth completion test | RMSE: 901.43 -> 915.86 | Hurt |
Closest papers by meaning
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.89)
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.89)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.88)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.88)
- Bilateral Propagation Network for Depth Completion (CVPR 2024 · similarity 0.87)
- Improving Depth Completion via Depth Feature Upsampling (CVPR 2024 · 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.