Check out our new #GAN work on person re-id. Training data is one of the keys to deep learning😈. Given N images, our #cvpr19 oral paper could generate O(NxN) high-fidelity images for training.
Paper link: https://arxiv.org/abs/1904.07223
Full Video: https://www.youtube.com/watch?v=ubCrEAIpQs4
#NVIDIA #UTS #ANU
Paper link: https://arxiv.org/abs/1904.07223
Full Video: https://www.youtube.com/watch?v=ubCrEAIpQs4
#NVIDIA #UTS #ANU
arXiv.org
Joint Discriminative and Generative Learning for Person Re-identification
Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to...
​​Neural network that turns sketches into realistic photo.
Paper is called «Semantic Image Synthesis with Spatially-Adaptive Normalization».
#CVPR19 oral paper on a new conditional normalization layer for semantic image synthesis #SPADE and its demo app #GauGAN
ArXiV: https://arxiv.org/abs/1903.07291
Website: https://nvlabs.github.io/SPADE/
#GAN #CV #DL
Paper is called «Semantic Image Synthesis with Spatially-Adaptive Normalization».
#CVPR19 oral paper on a new conditional normalization layer for semantic image synthesis #SPADE and its demo app #GauGAN
ArXiV: https://arxiv.org/abs/1903.07291
Website: https://nvlabs.github.io/SPADE/
#GAN #CV #DL
arXiv.org
Semantic Image Synthesis with Spatially-Adaptive Normalization
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout...