Research map / 3D vision / Gaussian splatting
Semi-Dense 3D Reconstruction with a Stereo Event Camera
Yi Zhou, Guillermo Gallego, Henri Rebecq, Laurent Kneip, Hongdong Li, Davide Scaramuzza
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 |
|---|---|---|---|
| use proposed forward-projection energy instead of FCVF stereo matching on time-surfaces | Event stereo reconstruction · Indoor flying1 | mean depth error (m): 0.99 -> 0.13 | Improved |
| use proposed energy instead of SGM on time-surfaces | Event stereo reconstruction · Indoor flying1 | mean depth error (m): 0.93 -> 0.13 | Improved |
| use proposed energy instead of FCVF | Event stereo reconstruction · Indoor flying3 | mean depth error (m): 1.03 -> 0.33 | Improved |
| use proposed energy instead of SGM | Event stereo reconstruction · Indoor flying3 | mean depth error (m): 1.19 -> 0.33 | Improved |
| use proposed energy instead of FCVF | Event stereo reconstruction · simulation 3planes | mean depth error (m): 0.05 -> 0.03 | Improved |
| use proposed energy instead of SGM | Event stereo reconstruction · simulation 3planes | relative depth error (%): 3.22 -> 1.17 | Improved |
| use proposed energy instead of FCVF | Event stereo reconstruction · Indoor flying1 | relative depth error (%): 20.8 -> 2.65 | Improved |
| use proposed energy instead of SGM | Event stereo reconstruction · Indoor flying3 | relative depth error (%): 20.8 -> 5.79 | Improved |
| fuse more neighboring reference view estimations (4, 8, 16) (ablation) | Probabilistic inverse depth fusion · Qualitative uncertainty maps | uncertainty / density | Improved |
Closest papers by meaning
- Deep Event Stereo Leveraged by Event-to-Image Translation (AAAI 2021 · similarity 0.90)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.89)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.87)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · 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.
