Research map / 3D vision / Depth and stereo
Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor
Andrea Conti, Matteo Poggi, Valerio Cambareri, Stefano Mattoccia
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 multi-view stereo cues to sparse-depth-only DoD (ablation) | DoD · ScanNetV2 | MAE: 0.049 -> 0.041 | Improved |
| add sparse depth cues to MVS-only DoD (ablation) | DoD · ScanNetV2 | F-Score: 0.530 -> 0.871 | Improved |
| add multi-view stereo cues to sparse-depth-only DoD for 3D reconstruction (ablation) | DoD · ScanNetV2 | F-Score: 0.870 -> 0.871 | No clear effect |
| estimate depth at RGB frame rate instead of the depth sensor frame rate (ablation) | DoD · ScanNetV2 3D reconstruction | F-Score: 0.856 -> 0.871 | Improved |
| inject sparse depth into MVS networks with only 2 views | Guided MVS networks · ScanNetV2 | MAE: 0.124 -> 0.286 (CAS-MVSNet, 8 to 2 views) | Hurt |
| use DoD instead of single-view depth completion on ScanNetV2 | temporal depth densification · ScanNetV2 | MAE: 0.067 -> 0.041 | Improved |
| use DoD on KITTI where multi-view overlap is small | DoD · KITTI LiDAR 1Hz | MAE: 0.348 -> 0.347 vs CompletionFormer | No clear effect |
Closest papers by meaning
- Estimating Depth from RGB and Sparse Sensing (ECCV 2018 · similarity 0.89)
- R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras (ICCV 2023 · similarity 0.88)
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · similarity 0.87)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.86)
- Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation (CVPR 2025 · similarity 0.86)
- Vision-Language Embodiment for Monocular Depth Estimation (CVPR 2025 · similarity 0.86)
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.
