Research map / 3D vision / Depth and stereo
Stereo Depth Estimation with Echoes
Chenghao Zhang, Kun Tian, Bolin Ni, Gaofeng Meng, Bin Fan, Zhaoxiang Zhang, Chunhong Pan
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 CVR (cross-modal volume refinement) to stereo network (ablation) | STEREO2DEPTH · Stereo-Replica | RMSE: 0.248 -> 0.202 | Improved |
| add CVR (cross-modal volume refinement) to stereo network (ablation) | STEREO2DEPTH · Stereo-Matterport3D | RMSE: 0.636 -> 0.593 | Improved |
| add RDUE (relative depth uncertainty estimation) to stereo network (ablation) | STEREO2DEPTH · Stereo-Replica | RMSE: 0.248 -> 0.193 | Improved |
| add RDUE (relative depth uncertainty estimation) to stereo network (ablation) | STEREO2DEPTH · Stereo-Matterport3D | RMSE: 0.636 -> 0.599 | Improved |
| add RDUE on top of CVR (ablation) | StereoEchoes · Stereo-Replica | RMSE: 0.202 -> 0.186 | Improved |
| add CVR on top of RDUE (ablation) | StereoEchoes · Stereo-Replica | RMSE: 0.193 -> 0.186 | Improved |
| add RDUE on top of CVR (ablation) | StereoEchoes · Stereo-Matterport3D | RMSE: 0.593 -> 0.548 | Improved |
| add CVR on top of RDUE (ablation) | StereoEchoes · Stereo-Matterport3D | RMSE: 0.599 -> 0.548 | Improved |
| use CVR instead of concatenating audio and stereo features (ablation) | StereoEchoes feature fusion · Stereo-Replica | RMSE: 0.228 -> 0.202 | Improved |
| use CVR instead of bilinear transformation with attention (ablation) | StereoEchoes feature fusion · Stereo-Replica | RMSE: 0.234 -> 0.202 | Improved |
| use relative uncertainty instead of simple averaging for output fusion (ablation) | StereoEchoes output fusion · Stereo-Replica | RMSE: 0.281 -> 0.193 | Improved |
| use relative uncertainty instead of single-modal stereo uncertainty (ablation) | StereoEchoes output fusion · Stereo-Replica | RMSE: 0.234 -> 0.193 | Improved |
Closest papers by meaning
- Beyond Image to Depth: Improving Depth Prediction Using Echoes (CVPR 2021 · similarity 0.92)
- EchoDiffusion: Waveform Conditioned Diffusion Models for Echo-Based Depth Estimation (AAAI 2025 · similarity 0.86)
- Learning Non-Volumetric Depth Fusion Using Successive Reprojections (CVPR 2019 · similarity 0.85)
- Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective With Transformers (ICCV 2021 · similarity 0.85)
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.83)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.83)
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.
