Research map / 3D vision / Depth and stereo
Dense Monocular Depth Estimation in Complex Dynamic Scenes
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 the proposed geometric reconstruction instead of depth transfer | Monocular depth estimation · KITTI odometry set | MRE: 0.171 -> 0.148 | Helped |
| Use the proposed geometric reconstruction instead of depth transfer | Monocular depth estimation · KITTI odometry set | log10 error: 0.076 -> 0.065 | Helped |
| Use the proposed geometric reconstruction instead of depth transfer | Monocular depth estimation · KITTI odometry set | RMSE: 2.830 -> 2.408 | Helped |
| Use the proposed approach rather than the strongest reported baseline | Monocular depth estimation · MPI Sintel final | MRE: 0.422 -> 0.297 | Helped |
| Use the proposed approach rather than the strongest reported baseline | Monocular depth estimation · MPI Sintel final | log10 error: 0.227 -> 0.146 | Helped |
| Use the proposed approach rather than the strongest reported baseline | Monocular depth estimation · MPI Sintel final | RMSE: 3.206 -> 2.458 | Helped |
| Use FlowFields instead of LDOF input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | MRE: 0.341 -> 0.297 | Helped |
| Use FlowFields instead of EpicFlow input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | MRE: 0.300 -> 0.297 | Helped |
| Use FlowFields instead of LDOF input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | log10 error: 0.154 -> 0.146 | Helped |
| Use FlowFields instead of EpicFlow input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | log10 error: 0.148 -> 0.146 | Helped |
| Use FlowFields instead of LDOF input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | RMSE: 2.576 -> 2.458 | Helped |
| Use FlowFields instead of EpicFlow input optical flow (ablation) | Proposed depth reconstruction · MPI Sintel final | RMSE: 2.575 -> 2.458 | Helped |
Closest papers by meaning
- Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.88)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.88)
- Align3R: Aligned Monocular Depth Estimation for Dynamic Videos (CVPR 2025 · similarity 0.87)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.87)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · 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.