Research map / Point clouds / Point cloud classification
Dense Depth Posterior (DDP) From Single Image and Sparse Range
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 a conditional depth prior learned from image-depth data (ablation) | DDP unsupervised depth completion · KITTI unsupervised test | iRMSE: 3.76 -> 3.58 | Helped |
| add raw stereo photometric supervision to the CPN-based loss (ablation) | DDP unsupervised depth completion · KITTI unsupervised test | iRMSE: 3.69 -> 3.63 | Helped |
| add SSIM photometric supervision alongside the raw photometric term (ablation) | DDP unsupervised depth completion · KITTI unsupervised test | RMSE: 1274.65 -> 1263.19 | Helped |
| include stereo photometric supervision (ablation) | DDP unsupervised depth completion · KITTI unsupervised test | RMSE: 1285.14 -> 1263.19 | Helped |
| use monocular rather than stereo supervision with CPN (ablation) | DDP · KITTI unsupervised test | iRMSE: 3.58 -> 3.67 | Hurt |
| increase sparse-depth input density (ablation) | DDP · NYUv2 test | RMSE: 3.829 -> 0.521 | Helped |
| use L1 for the sparse-measurement likelihood term rather than L2 (ablation) | DDP depth completion network · KITTI validation | RMSE | Helped |
| use L2 for the conditional-prior term (ablation) | DDP depth completion network · KITTI validation | RMSE | Helped |
Closest papers by meaning
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.90)
- Semi-Supervised Deep Learning for Monocular Depth Map Prediction (CVPR 2017 · similarity 0.89)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.89)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.88)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (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.