We study joint video and language (VL) pre-training to enable cross-moda...
We present a new perspective of achieving image synthesis by viewing thi...
Reshaping accurate and realistic 3D human bodies from anthropometric
par...
State-of-the-art image inpainting approaches can suffer from generating
...
High-quality video inpainting that completes missing regions in video fr...
High-quality image inpainting requires filling missing regions in a dama...