SCALAR: Scale-wise Controllable Visual Autoregressive Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914159548956672 |
|---|---|
| author | Xu, Ryan Jin, Dongyang Bai, Yancheng Lan, Rui Duan, Xu Sun, Lei Chu, Xiangxiang |
| author_facet | Xu, Ryan Jin, Dongyang Bai, Yancheng Lan, Rui Duan, Xu Sun, Lei Chu, Xiangxiang |
| contents | Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style. Existing VAR-based methods often suffer from inefficient control encoding and disruptive injection mechanisms that compromise both fidelity and efficiency. In this work, we present SCALAR, a controllable generation method based on VAR, incorporating a novel Scale-wise Conditional Decoding mechanism. SCALAR leverages a pretrained image encoder to extract semantic control signal encodings, which are projected into scale-specific representations and injected into the corresponding layers of the VAR backbone. This design provides persistent and structurally aligned guidance throughout the generation process. Building on SCALAR, we develop SCALAR-Uni, a unified extension that aligns multiple control modalities into a shared latent space, supporting flexible multi-conditional guidance in a single model. Extensive experiments show that SCALAR achieves superior generation quality and control precision across various tasks. The code is released at https://github.com/AMAP-ML/SCALAR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19946 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCALAR: Scale-wise Controllable Visual Autoregressive Learning Xu, Ryan Jin, Dongyang Bai, Yancheng Lan, Rui Duan, Xu Sun, Lei Chu, Xiangxiang Computer Vision and Pattern Recognition Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style. Existing VAR-based methods often suffer from inefficient control encoding and disruptive injection mechanisms that compromise both fidelity and efficiency. In this work, we present SCALAR, a controllable generation method based on VAR, incorporating a novel Scale-wise Conditional Decoding mechanism. SCALAR leverages a pretrained image encoder to extract semantic control signal encodings, which are projected into scale-specific representations and injected into the corresponding layers of the VAR backbone. This design provides persistent and structurally aligned guidance throughout the generation process. Building on SCALAR, we develop SCALAR-Uni, a unified extension that aligns multiple control modalities into a shared latent space, supporting flexible multi-conditional guidance in a single model. Extensive experiments show that SCALAR achieves superior generation quality and control precision across various tasks. The code is released at https://github.com/AMAP-ML/SCALAR. |
| title | SCALAR: Scale-wise Controllable Visual Autoregressive Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19946 |