SIGGRAPH-2022 Paper Digest

Every paper, ordered by impact or potential impact. About SIGGRAPH 2022

IDPaperAuthors
1Palette: Image-to-Image Diffusion Models
IF:9   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   Related Code   View    Save
Highlight: This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration.
Chitwan Saharia; William Chan; Huiwen Chang et al.
2StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
IF:7   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   Related Code   View    Save
Highlight: Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of 10242 at such a dataset scale.
Axel Sauer; Katja Schwarz; Andreas Geiger;
3Domain Enhanced Arbitrary Image Style Transfer Via Contrastive Learning
IF:5   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   Related Code   View    Save
Highlight: In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method.
Yuxin Zhang; Fan Tang; Weiming Dong et al.
4EAMM: One-Shot Emotional Talking Face Via Audio-Based Emotion-Aware Motion Model
IF:5   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: In this paper, we propose the Emotion-Aware Motion Model (EAMM) to generate one-shot emotional talking faces by involving an emotion source video.
Xinya Ji; Hang Zhou; Kaisiyuan Wang et al.
5CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
IF:5   Related Papers   Related Patents   Related Grants   Related Venues   Related Experts   View    Save
Highlight: In this work, we investigate how to effectively link the pretrained latent spaces of StyleGAN and CLIP, which in turn allows us to automatically extract semantically-labeled edit directions from StyleGAN, finding and naming meaningful edit operations, in a fully unsupervised setup, without additional human guidance.
Rameen Abdal; Peihao Zhu; John Femiani et al.

About SIGGRAPH 2022