My research interests lie in the area of Computer Vision and Graphics. Specifically, I'm particularly interested in audio-visual joint learning, 3D generative models, arbitrary style transfer and image generation.
Audio-visual joint learning
Arbitrary Style transfer
3D Generative model
Exchangeable Feature Alignment for Arbitrary Style Transfer
Chunjin Song*, Zhijie Wu*, Yang Zhou, Minglun Gong, Hui Huang
We introduce a novel global-to-local(G2L) approach for 3D model generation through building an adversarial network(GAN) assiciated with additional local discriminators to construct the overall structure of the shape while yielding more plausible part geometries.