Limited by the nature of the low-dimensional representational capacity o...
In contrast to fully supervised methods using pixel-wise mask labels,
bo...
In contrast to the fully supervised methods using pixel-wise mask labels...
Leveraging StyleGAN's expressivity and its disentangled latent codes,
ex...
This paper introduces DCT-Net, a novel image translation architecture fo...
Semantic segmentation on driving-scene images is vital for autonomous
dr...
Body reshaping is an important procedure in portrait photo retouching. D...
Different from general photo retouching tasks, portrait photo retouching...
This paper proposes a novel active boundary loss for semantic segmentati...
Semantic human matting aims to estimate the per-pixel opacity of the
for...