Research map / Video / Video segmentation and tracking
ARES: Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimation
Jie Long Lee, Gim Hee Lee
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 MCA fusion (ablation) | ARES · DSEC | scene flow EPE: 5.532 -> 4.608 | Improved |
| add MCA fusion (ablation) | ARES · DSEC | optical flow EPE: 0.694 -> 0.485 | Improved |
| add TDPF (ablation) | ARES · DSEC | scene flow EPE: 6.340 -> 4.608 | Improved |
| add TDPF (ablation) | ARES · DSEC | disparity EPE: 0.507 -> 0.502 | No clear effect |
| add self-supervised losses (ablation) | ARES · DSEC | scene flow EPE: 5.118 -> 4.608 | Improved |
| use DINOv3 backbone (ablation) | ARES · DSEC | scene flow EPE: 4.642 -> 4.608 | No clear effect |
| interleaved attention with shared projections instead of cross-attention only (ablation) | ARES MCA · DSEC | scene flow EPE: 5.349 -> 4.608 | Improved |
| fuse RGB and event instead of RGB only (ablation) | ARES · DSEC | scene flow EPE: 5.064 -> 4.608 | Improved |
| fuse RGB and event instead of event only (ablation) | ARES · DSEC | scene flow EPE: 4.973 -> 4.608 | Improved |
| fuse RGB and event instead of RGB only (ablation) | ARES · DSEC | disparity EPE: 0.487 -> 0.502 | Hurt |
| ARES vs RAFT-3D on scene flow | ARES · DSEC | scene flow EPE: 5.131 -> 4.608 | Improved |
| ARES vs EMatch on optical flow | ARES · DSEC | optical flow EPE: 0.452 -> 0.485 | Hurt |
Closest papers by meaning
- Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow (TPAMI 2025 · similarity 0.89)
- Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow (CVPR 2024 · similarity 0.89)
- EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes (NeurIPS 2025 · similarity 0.88)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.88)
- DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement (CVPR 2024 · similarity 0.87)
- Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes (NeurIPS 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.
