Research map / Video / Video generation
DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing
Hyeonho Jeong, Jinho Chang, Geon Yeong Park, Jong Chul Ye
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 spatial and temporal self-similarity matching losses to V-DDS (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | motion fidelity: 0.8426 -> 0.9259 | Improved |
| add temporal self-similarity loss on top of spatial (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | frame consistency: 0.9567 -> 0.9726 | Improved |
| add temporal self-similarity loss on top of spatial (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | Frame-LPIPS: 0.3186 -> 0.3042 | Improved |
| add bounding-box masks to filter V-DDS gradients (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | Frame-LPIPS: 0.3416 -> 0.3042 | Improved |
| add masks (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | motion fidelity: 0.8653 -> 0.9259 | Improved |
| add spatial and temporal self-similarity losses (ablation) | DreamMotion (ZeroScope) · 26 DAVIS/WebVid pairs | CLIP text alignment: 0.8202 -> 0.8209 | No clear effect |
| apply DreamMotion score-distillation editing instead of baselines | ZeroScope · 26 DAVIS/WebVid pairs (user study) | edit accuracy: 3.63 -> 4.14 | Improved |
| apply DreamMotion to cascaded Show-1 keyframes instead of VMC | Show-1 · cascaded video editing (user study) | structure and motion preservation: 3.35 -> 4.30 | 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.
- Tune-A-Video — Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (ICCV 2023) · better on 1 of 1 shared result
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
- DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation (ICLR 2025 · similarity 0.88)
- Rethinking Score Distillation as a Bridge Between Image Distributions (NeurIPS 2024 · similarity 0.88)
- Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation (NeurIPS 2024 · similarity 0.87)
- DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing (CVPR 2025 · similarity 0.87)
- RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models (CVPR 2024 · similarity 0.86)
- FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025 · similarity 0.86)
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.
