Research map / Video / Video generation
LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
Nan Chen, Mengqi Huang, Yihao Meng, Zhendong Mao
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 local memory to SketchDiT (ablation) | SketchDiT · Sakuga long-term (avg 500 frames) | FVD: 321.62 -> 315.05 | Improved |
| Add global memory to SketchDiT (ablation) | SketchDiT · Sakuga long-term (avg 500 frames) | FVD: 321.62 -> 297.93 | Improved |
| Use global memory instead of local memory (ablation) | SketchDiT · Sakuga long-term (avg 500 frames) | FVD: 315.05 -> 297.93 | Improved |
| Add full DGLM (global plus local memory) (ablation) | SketchDiT · Sakuga long-term (avg 500 frames) | FVD: 321.62 -> 261.76 | Improved |
| Add full DGLM (global plus local memory) (ablation) | SketchDiT · Sakuga long-term (avg 500 frames) | LPIPS: 0.086 -> 0.076 | Improved |
| Add Color Consistency Reward (ablation) | SketchDiT + DGLM · Sakuga long-term (avg 500 frames) | FVD: 261.76 -> 240.57 | Improved |
| Add Color Consistency Reward (ablation) | SketchDiT + DGLM · Sakuga long-term (avg 500 frames) | LPIPS: 0.076 -> 0.068 | Improved |
| Start color consistency fusion at t_st=20 (late denoising) (ablation) | LongAnimation · Sakuga long-term (avg 500 frames) | FVD: 266.99 -> 240.57 | Improved |
| Start color consistency fusion at t_st=50 (early denoising) (ablation) | LongAnimation · Sakuga long-term (avg 500 frames) | FVD: 266.99 -> 337.05 | Hurt |
| Start color consistency fusion at t_st=40 (early denoising) (ablation) | LongAnimation · Sakuga long-term (avg 500 frames) | FVD: 266.99 -> 301.62 | Hurt |
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.
- AniDoc — AniDoc: Animation Creation Made Easier (CVPR 2025) · better on 5 of 5 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
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.88)
- EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration (NeurIPS 2026 · similarity 0.87)
- A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural Awareness (ICCV 2025 · similarity 0.87)
- Image Referenced Sketch Colorization Based on Animation Creation Workflow (CVPR 2025 · similarity 0.87)
- MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model (CVPR 2024 · similarity 0.86)
- Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation (NeurIPS 2026 · 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.
