Research map / 3D vision / Depth and stereo
Disambiguating Monocular Depth Estimation with a Single Transient
Mark Nishimura, David B. Lindell, Christopher Metzler, Gordon Wetzstein
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 single-transient histogram matching (SBR=100) | DORN · NYU Depth v2 test (simulated transient) | rmse: 0.501 -> 0.408 | Improved |
| add single-transient histogram matching (SBR=100) | DenseDepth · NYU Depth v2 test (simulated transient) | rmse: 0.461 -> 0.346 | Improved |
| replace median rescaling with transient histogram matching (SBR=100) | DenseDepth · NYU Depth v2 test (simulated transient) | rmse: 0.409 -> 0.346 | Improved |
| replace median rescaling with transient histogram matching (SBR=100) | DORN · NYU Depth v2 test (simulated transient) | rmse: 0.473 -> 0.408 | Improved |
| raise signal-to-background ratio from 5 to 100 | DORN + proposed · NYU Depth v2 test (simulated transient) | rmse: 0.423 -> 0.408 | Improved |
| raise signal-to-background ratio from 5 to 100 | DenseDepth + proposed · NYU Depth v2 test (simulated transient) | rmse: 0.361 -> 0.346 | Improved |
| use noisy transient (SBR=100) instead of ground-truth histogram | DenseDepth + proposed · NYU Depth v2 test (simulated transient) | rmse: 0.338 -> 0.346 | Hurt |
| use noisy transient (SBR=100) instead of ground-truth histogram | MiDaS + proposed · NYU Depth v2 test (simulated transient) | rmse: 0.558 -> 0.570 | Hurt |
| raise signal-to-background ratio from 5 to 100 | MiDaS + proposed · NYU Depth v2 test (simulated transient) | rmse: 0.579 -> 0.570 | Improved |
| add diffused-SPAD transient correction on captured hallway and conference scenes | MiDaS · Captured prototype scenes | RMSE (m): 2.6-3.2 m -> 0.6-0.9 m | Improved |
Closest papers by meaning
- Dense Monocular Depth Estimation in Complex Dynamic Scenes (CVPR 2016 · similarity 0.89)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.88)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.87)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.87)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.87)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · 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.
