Research map / 3D vision / Depth and stereo
240FPS Stereo Vision from Monocular Mixed Spikes
Yeliduosi Xiaokaiti, Yakun Chang, Yang Bai, Zhaojun Huang, Peiqi Duan, Boxin Shi
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 SMS-Net refinement to least-squares baseline decoupling, DEFOM-Stereo depth | Baseline decoupling · TartanAir depth | AbsRel: 0.1695 -> 0.0940 | Improved |
| add SMS-Net refinement, CREStereo depth | Baseline decoupling · TartanAir depth | RMSE: 2.2064 -> 2.3595 | Mixed |
| add SMS-Net refinement, DEFOM-Stereo depth | Baseline decoupling · KITTI depth | RMSE: 4.8843 -> 4.1719 | Improved |
| add ABC module to baseline (ablation) | Baseline decoupling · TartanAir | PSNR left/right: 26.53/16.54 -> 32.13/28.22 | Improved |
| add CBA module to baseline (ablation) | Baseline decoupling · TartanAir | PSNR left/right: 26.53/16.54 -> 28.90/19.97 | Improved |
| add RSF module to baseline (ablation) | Baseline decoupling · TartanAir | PSNR left/right: 26.53/16.54 -> 32.00/32.29 | Improved |
| add CBA to ABC+RSF (full model) (ablation) | SMS-Net · TartanAir | PSNR left/right: 36.20/35.45 -> 36.97/35.73 | Improved |
| add ABC to CBA+RSF (full model) (ablation) | SMS-Net · TartanAir | PSNR left/right: 31.55/32.15 -> 36.97/35.73 | Improved |
| add RSF to ABC+CBA (ablation) | SMS-Net · TartanAir | PSNR left/right: 33.66/29.73 -> 36.97/35.73 | Improved |
| add full SMS-Net modules versus ABC+RSF (ablation) | SMS-Net · TartanAir | Bad 3.0: 4.691 -> 4.791 | No clear effect |
Closest papers by meaning
- Spike Transformer: Monocular Depth Estimation for Spiking Camera (ECCV 2022 · similarity 0.86)
- SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams (ICLR 2026 · similarity 0.86)
- Implicit View-Time Interpolation of Stereo Videos Using Multi-Plane Disparities and Non-Uniform Coordinates (CVPR 2023 · similarity 0.86)
- MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion (ICCV 2025 · similarity 0.85)
- Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues (CVPR 2025 · similarity 0.85)
- Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations (CVPR 2024 · similarity 0.84)
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.
