中文
相关论文

相关论文: MAST: Mask-Guided Attention Mass Allocation for Tr…

200 篇论文

Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image…

计算机视觉与模式识别 · 计算机科学 2023-07-12 Dan Ruta , Gemma Canet Tarrés , Andrew Gilbert , Eli Shechtman , Nicholas Kolkin , John Collomosse

The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes including semantic elements, object shapes, etc. Previous arbitrary…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Yuxin Zhang , Nisha Huang , Fan Tang , Haibin Huang , Chongyang Ma , Weiming Dong , Changsheng Xu

Recent advancements in graph neural networks (GNNs) have significantly enhanced the prediction of material properties by modeling crystal structures as graphs. However, GNNs often struggle to capture global structural characteristics, such…

机器学习 · 计算机科学 2025-08-11 Jaewan Lee , Changyoung Park , Hongjun Yang , Sungbin Lim , Woohyung Lim , Sehui Han

Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Jianyi Zhang , Yufan Zhou , Jiuxiang Gu , Curtis Wigington , Tong Yu , Yiran Chen , Tong Sun , Ruiyi Zhang

Recently, attentional arbitrary style transfer methods have been proposed to achieve fine-grained results, which manipulates the point-wise similarity between content and style features for stylization. However, the attention mechanism…

计算机视觉与模式识别 · 计算机科学 2022-01-10 Xuan Luo , Zhen Han , Lingkang Yang , Lingling Zhang

Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Lin Zhu , Xinbing Wang , Chenghu Zhou , Qinying Gu , Nanyang Ye

This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Quanjian Song , Mingbao Lin , Wengyi Zhan , Shuicheng Yan , Liujuan Cao , Rongrong Ji

Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstream tasks of interest. However, different downstream tasks…

机器学习 · 计算机科学 2023-03-08 Chen Huang , Hanlin Goh , Jiatao Gu , Josh Susskind

3D style transfer enables the creation of visually expressive 3D content, enriching the visual appearance of 3D scenes and objects. However, existing VGG- and CLIP-based methods struggle to model multi-view consistency within the model…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Yitong Yang , Xuexin Liu , Yinglin Wang , Jing Wang , Hao Dou , Changshuo Wang , Shuting He

Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning models generalize in data-scarce domains. While well developed…

Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extra computational costs, and feature misalignment. To address…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Nisha Huang , Henglin Liu , Yizhou Lin , Kaer Huang , Chubin Chen , Jie Guo , Tong-Yee Lee , Xiu Li

Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of…

计算机视觉与模式识别 · 计算机科学 2023-09-13 Haibo Chen , Lei Zhao , Jun Li , Jian Yang

Image Style Transfer (IST) is an interdisciplinary topic of computer vision and art that continuously attracts researchers' interests. Different from traditional Image-guided Image Style Transfer (IIST) methods that require a style…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Hanyu Wang , Pengxiang Wu , Kevin Dela Rosa , Chen Wang , Abhinav Shrivastava

We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style transfer models, e.g., CNN-based, ViT-based, and flow-based…

计算机视觉与模式识别 · 计算机科学 2023-03-24 Yuxin Zhang , Fan Tang , Weiming Dong , Haibin Huang , Chongyang Ma , Tong-Yee Lee , Changsheng Xu

In layout-to-image (L2I) synthesis, controlled complex scenes are generated from coarse information like bounding boxes. Such a task is exciting to many downstream applications because the input layouts offer strong guidance to the…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Ruyu Wang , Xuefeng Hou , Sabrina Schmedding , Marco F. Huber

This article presents a novel multi-agent spatial transformer (MAST) for learning communication policies in large-scale decentralized and collaborative multi-robot systems (DC-MRS). Challenges in collaboration in DC-MRS arise from: (i)…

机器人学 · 计算机科学 2025-09-23 Damian Owerko , Frederic Vatnsdal , Saurav Agarwal , Vijay Kumar , Alejandro Ribeiro

Style transfer, a pivotal task in image processing, synthesizes visually compelling images by seamlessly blending realistic content with artistic styles, enabling applications in photo editing and creative design. While mainstream…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Yingying Deng , Xiangyu He , Fan Tang , Weiming Dong , Xucheng Yin

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widely reported in literature, our empirical studies on four…

计算机视觉与模式识别 · 计算机科学 2021-04-21 Jiaxin Cheng , Ayush Jaiswal , Yue Wu , Pradeep Natarajan , Prem Natarajan

Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention…

计算机视觉与模式识别 · 计算机科学 2023-07-12 Baifeng Shi , Siyu Gai , Trevor Darrell , Xin Wang

Semantic segmentation models trained on synthetic data often perform poorly on real-world images due to domain gaps, particularly in adverse conditions where labeled data is scarce. Yet, recent foundation models enable to generate realistic…

计算机视觉与模式识别 · 计算机科学 2025-09-19 Estelle Chigot , Dennis G. Wilson , Meriem Ghrib , Thomas Oberlin