Timezone: »

The Image Local Autoregressive Transformer
Chenjie Cao · Yuxin Hong · Xiang Li · Chengrong Wang · Chengming Xu · Yanwei Fu · Xiangyang Xue

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ Virtual

Recently, AutoRegressive (AR) models for the whole image generation empowered by transformers have achieved comparable or even better performance compared to Generative Adversarial Networks (GANs). Unfortunately, directly applying such AR models to edit/change local image regions, may suffer from the problems of missing global information, slow inference speed, and information leakage of local guidance. To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis. Our iLAT learns the novel local discrete representations, by the newly proposed local autoregressive (LA) transformer of the attention mask and convolution mechanism. Thus iLAT can efficiently synthesize the local image regions by key guidance information. Our iLAT is evaluated on various locally guided image syntheses, such as pose-guided person image synthesis and face editing. Both quantitative and qualitative results show the efficacy of our model.

Author Information

Chenjie Cao (Fudan university)
Yuxin Hong (Fudan University)
Xiang Li (Fudan University)
Chengrong Wang (Fudan University)
Chengming Xu (Fudan University)
Yanwei Fu (Fudan University, Shanghai;)
Xiangyang Xue (Fudan University)

More from the Same Authors