Research map / 3D vision / Depth and stereo
Distortion and Uncertainty Aware Loss for Panoramic Depth Completion
Zhiqiang Yan, Xiang Li, Kun Wang, Shuo Chen, Jun Li, Jian Yang
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 |
|---|---|---|---|
| train with LDU loss instead of raw loss (ablation) | M3PT · Matterport3D | RMSE (mm): 138.9 -> 114.9 | Improved |
| train with LDU loss instead of raw loss (ablation) | M3PT · Matterport3D | MRE: 0.0164 -> 0.0162 | No clear effect |
| train with LDU loss instead of raw loss (ablation) | GuideNet · Matterport3D | RMSE (mm): 192.9 -> 164.8 | Improved |
| train with LDU loss instead of raw loss (ablation) | HoHo-R · Matterport3D | RMSE (mm): 199.2 -> 168.8 | Improved |
| train with LDU loss instead of raw loss (ablation) | HoHo-R · 3D60 | RMSE (mm): 196.9 -> 168.3 | Improved |
| train with LDU loss instead of raw loss (ablation) | GuideNet · 3D60 | RMSE (mm): 239.3 -> 192.3 | Improved |
| add distortion-aware loss LDA only (ablation) | M3PT · Matterport3D and 3D60 | RMSE: 5.9mm and 8.4mm reduction | Improved |
| add consistent uncertainty estimation LCUE on top of LUA (ablation) | M3PT · Matterport3D and 3D60 | RMSE: 15.7mm and 19.4mm reduction | Improved |
| combine all three losses (LDU) (ablation) | M3PT · Matterport3D and 3D60 | RMSE: 23.9mm and 24.1mm reduction | Improved |
| use uncertainty maps from convolution plus horizontal flip instead of convolution only (ablation) | M3PT LCUE · Matterport3D | RMSE (mm): 129.6 -> 123.2 | Improved |
| use vertical flip pair HF,VF instead of C,HF (ablation) | M3PT LCUE · Matterport3D | RMSE (mm): 123.2 -> 124.7 | Hurt |
| increase number of uncertainty maps from 2 to 4 (ablation) | M3PT LCUE · Matterport3D | RMSE (mm): 123.2 -> 123.0 | 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.
- ACDNet — ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation (AAAI 2022) · better on 2 of 2 shared results
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
- Robust Depth Completion with Uncertainty-Driven Loss Functions (AAAI 2022 · similarity 0.89)
- Revisiting Gradient-Based Uncertainty for Monocular Depth Estimation (TPAMI 2025 · similarity 0.88)
- Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images (ECCV 2018 · similarity 0.87)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.85)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.85)
- PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness (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.
