34 citations · 43 across the 7 of their papers we have counts for
7 papers
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
Yaohui Wang, Xinyuan Chen, Xin Ma +17
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challengi…
LEO: Generative Latent Image Animator for Human Video Synthesis
Yaohui Wang, Xin Ma, Xinyuan Chen +4
Spatio-temporal coherency is a major challenge in synthesizing high quality videos, particularly in synthesizing human videos that contain rich global and local deformations. To re…
Compressing Models with Few Samples: Mimicking then Replacing
Huanyu Wang, Junjie Liu, Xin Ma +3
Few-sample compression aims to compress a big redundant model into a small compact one with only few samples. If we fine-tune models with these limited few samples directly, models…
Contrastive Attention Network with Dense Field Estimation for Face Completion
Xin Ma, Xiaoqiang Zhou, Huaibo Huang +3
Most modern face completion approaches adopt an autoencoder or its variants to restore missing regions in face images. Encoders are often utilized to learn powerful representations…
Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion
Yuhe Ding, Xin Ma, Mandi Luo +2
Photo-to-caricature translation aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style…
Free-Form Image Inpainting via Contrastive Attention Network
Xin Ma, Xiaoqiang Zhou, Huaibo Huang +3
Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representa…
Exploiting Style and Attention in Real-World Super-Resolution
Xin Ma, Yi Li, Huaibo Huang +2
Real-world image super-resolution (SR) is a challenging image translation problem. Low-resolution (LR) images are often generated by various unknown transformations rather than by…