paper-with-me

Papers

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

2020-07-23 · ECCV 2020 8 · Liming Jiang, Changxu Zhang, Mingyang Huang, Chunxiao Liu, Jianping Shi, Chen Change Loy

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.

📄 PDF Abstract BibTeX arXiv:2007.12072

Code (1)

EndlessSora/TSIT 공식 구현 pytorch

Tasks

Image GenerationImage-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Planet as a Brain: Towards Internet of AgentSites based on AIOS Server

2025-04-19 · Xiang Zhang, Yongfeng Zhang

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 Agent

SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition

2019-03-14 · Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang 외

A Simple and Versatile Framework for Object Detection and Instance Recognition

Autonomous DrivingMedical Image AnalysisObjectobject-detection+1

On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning

2020-02-10 · ICLR 2022 4 · Che Wang, Shuhan Yuan, Kai Shao, Keith Ross

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

2022-07-11 · Zijie Wu, Zhen Zhu, Junping Du, Xiang Bai

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 Transfer

LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs

2025-12-23 · Haiyun Wei, Fan Lu, Yunwei Zhu, Zehan Zheng 외 arxiv

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