InstanceAnimator: Multi-Instance Sketch Video Colorization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914424852316160 |
|---|---|
| author | Zhang, Yinhan Ma, Yue Wang, Bingyuan Feng, Kunyu Jin, Yeying Chen, Qifeng Rao, Anyi Wang, Zeyu |
| author_facet | Zhang, Yinhan Ma, Yue Wang, Bingyuan Feng, Kunyu Jin, Yeying Chen, Qifeng Rao, Anyi Wang, Zeyu |
| contents | We propose InstanceAnimator, a novel Diffusion Transformer framework for multi-instance sketch video colorization. Existing methods suffer from three core limitations: inflexible user control due to heavy reliance on single reference frames, poor instance controllability leading to misalignment in multi-character scenarios, and degraded detail fidelity in fine-grained regions. To address these challenges, we introduce three corresponding innovations. First, a Canvas Guidance Condition eliminates workflow fragmentation by allowing free placement of reference elements and background, enabling unprecedented user flexibility. Second, an Instance Matching Mechanism resolves misalignment by integrating instance features with the sketches, ensuring precise control over multiple characters. Third, an Adaptive Decoupled Control Module enhances detail fidelity by injecting semantic features from characters, backgrounds, and text conditions into the diffusion process. Extensive experiments demonstrate that InstanceAnimator achieves superior multi-instance colorization with enhanced user control, high visual quality, and strong instance consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25357 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InstanceAnimator: Multi-Instance Sketch Video Colorization Zhang, Yinhan Ma, Yue Wang, Bingyuan Feng, Kunyu Jin, Yeying Chen, Qifeng Rao, Anyi Wang, Zeyu Computer Vision and Pattern Recognition We propose InstanceAnimator, a novel Diffusion Transformer framework for multi-instance sketch video colorization. Existing methods suffer from three core limitations: inflexible user control due to heavy reliance on single reference frames, poor instance controllability leading to misalignment in multi-character scenarios, and degraded detail fidelity in fine-grained regions. To address these challenges, we introduce three corresponding innovations. First, a Canvas Guidance Condition eliminates workflow fragmentation by allowing free placement of reference elements and background, enabling unprecedented user flexibility. Second, an Instance Matching Mechanism resolves misalignment by integrating instance features with the sketches, ensuring precise control over multiple characters. Third, an Adaptive Decoupled Control Module enhances detail fidelity by injecting semantic features from characters, backgrounds, and text conditions into the diffusion process. Extensive experiments demonstrate that InstanceAnimator achieves superior multi-instance colorization with enhanced user control, high visual quality, and strong instance consistency. |
| title | InstanceAnimator: Multi-Instance Sketch Video Colorization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.25357 |