Shiqiu Liu — accepted AI-conference papers

2026

PixelDiT: Pixel Diffusion Transformers for Image Generation

Yongsheng Yu, Wei Xiong, Weili Nie, Yichen Sheng, Shiqiu Liu, Jiebo Luo

CVPR 2026

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint optimization. To address these issues, we propose PixelDiT,

Cited by 0 Source ↗code ↗Scholar ↗

2020

Neural FFTs for Universal Texture Image Synthesis

Morteza Mardani, Guilin Liu, Aysegul Dundar, Shiqiu Liu, Andrew Tao, Bryan Catanzaro

NeurIPS 2020poster

Synthesizing larger texture images from a smaller exemplar is an important task in graphics and vision. The conventional CNNs, recently adopted for synthesis, require to train and test on the same set of images and fail to generalize to unseen images. This is mainly because those CNNs fully rely on…

Cited by 37 Source ↗PDF ↗Scholar ↗