TSIT: A Simple and Versatile Framework for Image-to-Image Translation
We introduce a simple and versatile framework for image-to-image translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generative model with newly proposed feature transformations in a coarse-to-fine fashion. This allows multi-scale semantic structure information and style representation to be effectively captured and fused by the network, permitting our method to scale to various tasks in both unsupervised and supervised settings. No additional constraints (e.g., cycle consistency) are needed, contributing to a very clean and simple method. Multi-modal image synthesis with arbitrary style control is made possible. A systematic study compares the proposed method with several state-of-the-art task-specific baselines, verifying its effectiveness in both perceptual quality and quantitative evaluations.
Code (1)
Tasks
Image GenerationImage-to-Image TranslationTranslationSimilar Papers 제목 키워드 기반
Planet as a Brain: Towards Internet of AgentSites based on AIOS Server
The internet is undergoing a historical transformation from the "Internet of Websites" to the "Internet of AgentSites." While traditional Websites served as the foundation for information hosting and dissemination, a new…
AI AgentSimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
A Simple and Versatile Framework for Object Detection and Instance Recognition
Autonomous DrivingMedical Image AnalysisObjectobject-detection+1On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing action…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
In this paper, we aim to devise a universally versatile style transfer method capable of performing artistic, photo-realistic, and video style transfer jointly, without seeing videos during training. Previous single-fram…
Image-to-Image TranslationStyle TransferVideo Style TransferLiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs
Generating realistic and diverse LiDAR point clouds is crucial for autonomous driving simulation. Although previous methods achieve LiDAR point cloud generation from user inputs, they struggle to attain high-quality resu…
Point Cloud GenerationAutonomous DrivingPoint Clouds