Research map / 3D vision / Depth and stereo
Self-Supervised Deep Depth Denoising
Vladimiros Sterzentsenko, Leonidas Saroglou, Anargyros Chatzitofis, Spyridon Thermos, Nikolaos Zioulis, Alexandros Doumanoglou, Dimitrios Zarpalas, Petros Daras
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 photometric multi-view supervision instead of plain autoencoder reconstruction (ablation) | self-supervised denoiser · D415 test set (70 pairs, K2 reference) | MAE (mm): 26.35 -> 25.96 | Improved |
| add photometric supervision instead of plain autoencoder (ablation) | self-supervised denoiser · D415 test set (70 pairs, K2 reference) | RMSE (mm): 59.92 -> 58.30 | Improved |
| add BerHu depth regularization to photometric loss (ablation) | P-only · D415 test set (70 pairs, K2 reference) | MAE (mm): 25.96 -> 26.43 | Hurt |
| add BerHu depth regularization to photometric loss (ablation) | P-only · D415 test set (70 pairs, K2 reference) | Normal angle within 30 deg (%): 53.11 -> 53.98 | Improved |
| add normal smoothness prior to photometric loss (no depth term) (ablation) | P-only · D415 test set (70 pairs, K2 reference) | MAE (mm): 25.96 -> 28.04 | Hurt |
| add normal prior on top of photometric plus depth loss (ablation) | P+D · D415 test set (70 pairs, K2 reference) | MAE (mm): 26.43 -> 25.11 | Improved |
| add normal prior on top of photometric plus depth loss (ablation) | P+D · D415 test set (70 pairs, K2 reference) | RMSE (mm): 58.31 -> 58.95 | Hurt |
| add depth loss to photometric plus normal prior (ablation) | P+N · D415 test set (70 pairs, K2 reference) | MAE (mm): 28.04 -> 25.11 | Improved |
| use proposed self-supervised model instead of DRR (ablation) | DRR · InteriorNet (synthetic noise) | MAE: 86.88 -> 33.44 | Improved |
| train DDRNet on our dataset with partial convolutions instead of traditional | DDRNet retrained · D415 test set (70 pairs, K2 reference) | MAE (mm): 121.83 -> 75.68 | Improved |
| use our model instead of DDRNet-PC retrained on our data | DDRNet-PC · D415 test set (70 pairs, K2 reference) | MAE (mm): 75.68 -> 25.11 | Improved |
| use our model instead of RGF for KinectFusion | RGF · KinectFusion reconstruction (15 sequences) | point-to-plane RMSE (mm): 32.58 -> 24.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DDRNet — DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019 · similarity 0.90)
- Self-Supervised Learning of Depth Inference for Multi-View Stereo (CVPR 2021 · similarity 0.89)
- Self-Supervised Deep Monocular Depth Estimation With Ambiguity Boosting (TPAMI 2021 · similarity 0.89)
- Multi-Resolution Monocular Depth Map Fusion by Self-Supervised Gradient-Based Composition (AAAI 2023 · similarity 0.89)
- DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation (ECCV 2024 · similarity 0.89)
- Self-Distilled Depth Refinement with Noisy Poisson Fusion (NeurIPS 2024 · similarity 0.88)
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.
