Toward Multimodal Image-to-Image Translation
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), pp. 465-476, 2017.
We explore two ways of propagating the latent code z to the output, as shown in Figure 3: add_to_input: we spatially replicate a Z-dimensional latent code z to an H × W × Z tensor and concatenate it with the H × W × 3 input image and add_to_all: we add z to each intermediate laye...
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a distribution of possible outputs in a conditional generative modeling setting. The ambiguity of the mapping is distilled in a low-dimensional latent vector, which can be randomly samp...More
PPT (Upload PPT)