Research map / Video / Video segmentation and tracking
EDM:Event-guided Diffusion Model for Video Shadow Detection in Complex Dynamic Scenes
boyang gao, jiayi guo, Ziyu Wang, Yingbin Cui, Zhan Tu
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 MTA module (ablation) | EDM · Event-ViSha | BER: 7.35 -> 5.76 | Improved |
| add BMG module (ablation) | EDM · Event-ViSha | BER: 6.64 -> 5.76 | Improved |
| add DMTG module (ablation) | EDM · Event-ViSha | BER: 8.72 -> 5.76 | Improved |
| add event stream input (ablation) | EDM · EVSD | BER: 17.32 -> 11.05 | Improved |
| add event stream input (ablation) | EDM · Event-ViSha | BER: 9.88 -> 5.76 | Improved |
| use event-based motion encoder instead of RGB optical flow (ablation) | EDM MTA · EVSD | BER: 13.97 -> 11.05 | Improved |
| use event-based motion encoder instead of event optical flow (E-RAFT) (ablation) | EDM MTA · EVSD | BER: 12.86 -> 11.05 | Improved |
| use 32x32 patches instead of 16x16 (ablation) | EDM MTA · Event-ViSha | BER: 6.89 -> 5.76 | Improved |
| use 32x32 patches instead of 64x64 (ablation) | EDM MTA · Event-ViSha | BER: 6.23 -> 5.76 | Improved |
| use bidirectional instead of unidirectional weighting in BMG (ablation) | EDM BMG · EVSD | BER: 11.47 -> 11.05 | Improved |
| add event-based preliminary mask in DMTG (ablation) | EDM DMTG · EVSD | BER: 14.69 -> 11.05 | Improved |
| use ESI representation instead of voxel grid (ablation) | EDM DMTG · EVSD | BER: 17.94 -> 11.05 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DTTNet — DTTNet: Improving Video Shadow Detection via Dark-Aware Guidance and Tokenized Temporal Modeling (AAAI 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- E-Motion: Future Motion Simulation via Event Sequence Diffusion (NeurIPS 2024 · similarity 0.86)
- LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction (NeurIPS 2024 · similarity 0.86)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.85)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.85)
- Emergent Temporal Correspondences from Video Diffusion Transformers (NeurIPS 2025 · similarity 0.85)
- DiffDVC: Accurate Event Detection for Dense Video Captioning via Diffusion Models (AAAI 2025 · similarity 0.85)
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.
