Research map / Video / Video generation
EasyCreator: Empowering 4D Creation through Video Inpainting
Yue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu, David Junhao Zhang, Jinbo Xing, Yinhan Zhang, Xiangpeng Yang, Xinyu Wang, Zeyu Wang, Qifeng Chen
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 composite mask training (ablation) | EasyCreator · Ablation | FID: 78.27 -> 58.26 | Improved |
| add composite mask training (ablation) | EasyCreator · Ablation | matched pixels (K): 518.21 -> 705.34 | Improved |
| add self-iterative tuning (ablation) | EasyCreator · Ablation | FID: 86.29 -> 58.26 | Improved |
| add self-iterative tuning (ablation) | EasyCreator · Ablation | FVD: 197.24 -> 145.71 | Improved |
| add self-iterative tuning (ablation) | EasyCreator · Ablation | CLIP-V: 81.26 -> 89.87 | Improved |
| add temporal-packing inference (ablation) | EasyCreator · Ablation | matched pixels (K): 524.63 -> 705.34 | Improved |
| add temporal-packing inference (ablation) | EasyCreator · Ablation | FVD-V: 137.64 -> 119.52 | Improved |
| add temporal-packing inference (ablation) | EasyCreator · Ablation | CLIP-F: 93.44 -> 96.62 | Improved |
| add composite mask training (ablation) | EasyCreator · Ablation | CLIP-T: 30.81 -> 35.63 | Improved |
| add self-iterative tuning (ablation) | EasyCreator · Ablation | CLIP-T: 36.58 vs 35.63 | No clear effect |
| add uncertainty estimation (UC) (ablation) | EasyCreator · Ablation (Table 8) | FID: 58.26 -> 56.84 | Improved |
| use Marigold depth estimator instead of DepthCrafter | EasyCreator · depth estimators (Table 7) | FID: 58.26 -> 63.78 | 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.
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · 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
- Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects (CVPR 2025 · similarity 0.88)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.87)
- EG4D: Explicit Generation of 4D Object without Score Distillation (ICLR 2025 · similarity 0.87)
- Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion (CVPR 2024 · similarity 0.86)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.86)
- Robust Multi-Object 4D Generation for In-the-wild Videos (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.
