Research map / Video / Video generation
Image Guides Images: Consistent Video Amodal Completion with Rectified In-Context Exemplar Guidance
Xiaoyu Kong, Ketong Ren, Dongyu She, Weiming Dong, Miao Wang
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 vanilla in-context learning with a single-frame inpainted exemplar (ablation) | IC-Amodal (Flux.1-Fill) · Kubric-Dynamic | FVD: 278.25 -> 301.83 | Hurt |
| add calibrated dual-frame exemplar rectification (ablation) | IC-Amodal · Kubric-Dynamic | FVD: 301.83 -> 219.37 | Improved |
| add rectified exemplar-guided attention completion (ablation) | IC-Amodal · Kubric-Dynamic | FVD: 219.37 -> 188.81 | Improved |
| add rectified exemplar-guided attention completion (ablation) | IC-Amodal · Kubric-Dynamic | PSNR: 24.50 -> 24.71 | Improved |
| use completed object (no scene context) as exemplar input Xex (ablation) | IC-Amodal · Kubric-Dynamic | IoU: 86.6 -> 83.1 | Hurt |
| use only visible part as exemplar input Xex instead of original frame (ablation) | IC-Amodal · Kubric-Dynamic | FVD: 188.81 -> 231.55 | Hurt |
| set amplification weight lambda-up to 1.5 (too small) (ablation) | rectified attention · Kubric | qualitative | Hurt |
| set amplification weight lambda-up to 5.0 (too large) (ablation) | rectified attention · Kubric | qualitative | Hurt |
| set attenuation weight lambda-down to 0.7 (too large) (ablation) | rectified attention · Kubric | qualitative | Hurt |
| blend raw completion with the original visible region (IC-Amodal+) | IC-Amodal · Kubric-Dynamic | PSNR: 24.705 -> 30.091 | Improved |
| use IC-Amodal instead of fine-tuned TACO (training-free vs finetuned) | IC-Amodal · Kubric-Dynamic | FVD: 209.28 -> 188.81 | Improved |
| use IC-Amodal instead of TACO | IC-Amodal · Kubric-Static | FVD: 162.91 -> 184.10 | 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.
- TACO — TACo: Token-Aware Cascade Contrastive Learning for Video-Text Alignment (ICCV 2021) · better on 9 of 10 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
- Using Diffusion Priors for Video Amodal Segmentation (CVPR 2025 · similarity 0.87)
- MaGIC: Multi-modality Guided Image Completion (ICLR 2024 · similarity 0.85)
- Amodal Ground Truth and Completion in the Wild (CVPR 2024 · similarity 0.84)
- Memory-Augmented Re-Completion for 3D Semantic Scene Completion (AAAI 2025 · similarity 0.84)
- Open-World Amodal Appearance Completion (CVPR 2025 · similarity 0.84)
- Sample-specific Masks for Visual Reprogramming-based Prompting (ICML 2024 · similarity 0.84)
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.
