Research map / Detection and segmentation / Tracking
Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
Jingyu Liu, Zijie Xin, Yuhan Fu, Ruixiang Zhao, Bangxiang Lan, Xirong Li
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 LLM motion plan (coarse object motion) (ablation) | MoSketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.212 -> 0.218 | Improved |
| add LLM motion plan (coarse object motion) (ablation) | MoSketch · Multi-object sketches (60 created) | Dynamic Degree: 0.083 -> 0.283 | Improved |
| add object-level refinement (ablation) | MoSketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.212 -> 0.218 | Improved |
| add point-level refinement (ablation) | MoSketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.203 -> 0.218 | Improved |
| add point-level refinement (ablation) | MoSketch · Multi-object sketches (60 created) | Dynamic Degree: 0.200 -> 0.283 | Improved |
| add object-aware network instead of Live-Sketch network (ablation) | MoSketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.205 -> 0.218 | Improved |
| add compositional SDS (ablation) | MoSketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.207 -> 0.218 | Improved |
| add compositional SDS (ablation) | MoSketch · Multi-object sketches (60 created) | Motion Smoothness: 0.966 -> 0.977 | Improved |
| add point-level refinement (ablation) | MoSketch · Multi-object sketches (60 created) | Sketch-to-Video Alignment: 0.971 -> 0.914 | Hurt |
| MoSketch vs Live-Sketch | Live-Sketch · Multi-object sketches (60 created) | Text-to-Video Alignment: 0.207 -> 0.218 | Improved |
| MoSketch vs Live-Sketch on freehand sketches | Live-Sketch · FS-COCO freehand (30 sketches) | Text-to-Video Alignment: 0.173 -> 0.197 | Improved |
| MoSketch on single-object sketches | Live-Sketch · Single-object sketches | Text-to-Video Alignment: 0.217 -> 0.209 | Hurt |
Closest papers by meaning
- FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations (CVPR 2025 · similarity 0.88)
- SketchVideo: Sketch-based Video Generation and Editing (CVPR 2025 · similarity 0.86)
- Breathing Life Into Sketches Using Text-to-Video Priors (CVPR 2024 · similarity 0.84)
- One-Shot Reference-based Structure-Aware Image to Sketch Synthesis (AAAI 2025 · similarity 0.83)
- AirSketch: Generative Motion to Sketch (NeurIPS 2024 · similarity 0.82)
- Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering (ICLR 2025 · similarity 0.82)
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.
