Conditional Image Generation with PixelCNN Decoders

NeurIPS 2016 Aaron van den OordNal KalchbrennerOriol VinyalsLasse EspeholtAlex GravesKoray Kavukcuoglu

This work explores conditional image generation with a new image density model based on the PixelCNN architecture. The model can be conditioned on any vector, including descriptive labels or tags, or latent embeddings created by other networks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation CIFAR-10 Gated PixelCNN bits/dimension 3.03 # 12
Image Generation ImageNet 32x32 Gated PixelCNN bpd 3.83 # 3
Image Generation ImageNet 64x64 Gated PixelCNN (van den Oord et al., [2016c]) Bits per dim 3.57 # 4

Methods used in the Paper