Research map / 3D vision / Depth and stereo
Event-Based Stereo Depth Estimation: A Survey
Suman Ghosh, Guillermo Gallego
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 frames to events (hybrid event+frame input, Conc-Net) | Conc-Net · DSEC disparity | MAE [px]: 0.520 -> 0.364 | Improved |
| add frames to events (EIS vs ES) | ES · DSEC disparity | MAE [px]: 0.529 -> 0.396 | Improved |
| use stereo instead of monocular event depth (MC-EMVS vs EMVS) | EMVS · MVSEC indoor flying split 1 | mean depth error [cm]: 39.37 -> 22.53 | Improved |
| use stereo instead of monocular event depth (MC-EMVS vs EMVS) | EMVS · DSEC zurich city 04a | mean error [cm]: 517.24 -> 313.18 | Improved |
| aggregate temporal information consistently (StereoFlow-Net vs DDES) | DDES · DSEC disparity | MAE [px]: 0.576 -> 0.493 | Improved |
| use supervised instead of unsupervised training | unsupervised stereo · DSEC disparity | MAE [px]: 0.771 -> 0.493 | Improved |
| use ESVO/MC-EMVS instead of SGM on time surfaces | SGM (Time Surf.) · MVSEC indoor flying split 1 | mean depth error [cm]: 35.45 -> 22.53 | Improved |
| use ES-PTAM instead of MC-EMVS | MC-EMVS · DSEC zurich city 04a | mean error [cm]: 313.18 -> 289.71 | Improved |
| use learning-based instantaneous instead of model-based long-term methods | model-based · MVSEC indoor flying | mean depth error [cm]: 22.53 -> 9.7 | Mixed |
Closest papers by meaning
- Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds (ICCV 2021 · similarity 0.92)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.92)
- Selection and Cross Similarity for Event-Image Deep Stereo (ECCV 2022 · similarity 0.91)
- A Low Power, High Throughput, Fully Event-Based Stereo System (CVPR 2018 · similarity 0.91)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.90)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.89)
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.
