Semantic Image Synthesis With Spatially-Adaptive Normalization
Taesung Park,Ming-Yu Liu,Ting-Chun Wang,Jun-Yan Zhu +3 more
- pp 2337-2346
Reads0
Chats0
TLDR
S spatially-adaptive normalization is proposed, a simple but effective layer for synthesizing photorealistic images given an input semantic layout that allows users to easily control the style and content of image synthesis results as well as create multi-modal results.Abstract:
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 as input to the network, forcing the network to memorize the information throughout all the layers. Instead, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned affine transformation. Experiments on several challenging datasets demonstrate the superiority of our method compared to existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows users to easily control the style and content of image synthesis results as well as create multi-modal results. Code is available upon publication.read more
Citations
More filters
BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models
TL;DR: Zhang et al. as mentioned in this paper proposed a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM), which models image to image translation as a stochastic Brownian bridge process and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process.
Posted Content
Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization.
TL;DR: Wang et al. as discussed by the authors proposed a spatially-adaptive warped normalization (SAWN) to align person spatialadaptive styles with pose features efficiently, which integrates a learned flow-field to warp modulation parameters.
Proceedings ArticleDOI
Adaptive Affine Transformation: A Simple and Effective Operation for Spatial Misaligned Image Generation
Zhimeng Zhang,Yuju Ding +1 more
TL;DR: This work proposes one simple but effective operator named AdaAT (Adaptive Affine Transformation) to realize misaligned image generation, which simulates spatial deformation by computing hundreds of affine transformations, resulting in less distortions.
Book ChapterDOI
Content Adaptive Latents and Decoder for Neural Image Compression
TL;DR: Wang et al. as mentioned in this paper proposed a new NIC framework that improves the content adaptability on both latents and the decoder, which automatically selects the optimal quality levels for the latents spatially and drops the redundant channels.
Book ChapterDOI
Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment
TL;DR: Li et al. as mentioned in this paper designed a new 3DMM-assisted warping-based face re-actment architecture which consists of two fast and efficient sub-networks, i.e., a u-shaped rendering network to reenact faces driven by head poses and facial motion fields, and a hierarchical coarse-to-fine motion network to predict facial motion field guided by different scales of landmark images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.