中文
相关论文

相关论文: Modeling the Lighting in Scenes as Style for Auto …

200 篇论文

We propose to improve multi-concept prompt fidelity in text-to-image diffusion models. We begin with common failure cases - prompts like "a cat and a dog" that sometimes yields images where one concept is missing, faint, or colliding…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Debottam Dutta , Jianchong Chen , Rajalaxmi Rajagopalan , Yu-Lin Wei , Romit Roy Choudhury

Recent advances in latent diffusion models have enabled exciting progress in image style transfer. However, several key issues remain. For example, existing methods still struggle to accurately match styles. They are often limited in the…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Dan Ruta , Abdelaziz Djelouah , Raphael Ortiz , Christopher Schroers

This paper proposes a novel luminance adjustment method based on automatic exposure compensation for multi-exposure image fusion. Multi-exposure image fusion is a method to produce images without saturation regions, by using photos with…

计算机视觉与模式识别 · 计算机科学 2018-05-30 Yuma Kinoshita , Sayaka Shiota , Hitoshi Kiya

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Jiexuan Zhang , Yiheng Du , Qian Wang , Weiqi Li , Yu Gu , Jian Zhang

In this work, we study the problem of word-level confidence calibration for scene-text recognition (STR). Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and…

计算机视觉与模式识别 · 计算机科学 2020-12-24 Ron Slossberg , Oron Anschel , Amir Markovitz , Ron Litman , Aviad Aberdam , Shahar Tsiper , Shai Mazor , Jon Wu , R. Manmatha

Utilizing the trained model under different conditions without data annotation is attractive for robot applications. Towards this goal, one class of methods is to translate the image style from another environment to the one on which models…

计算机视觉与模式识别 · 计算机科学 2021-03-11 Zexi Chen , Jiaxin Guo , Xuecheng Xu , Yunkai Wang , Yue Wang , Rong Xiong

Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require…

计算机视觉与模式识别 · 计算机科学 2024-11-13 Haian Jin , Yuan Li , Fujun Luan , Yuanbo Xiangli , Sai Bi , Kai Zhang , Zexiang Xu , Jin Sun , Noah Snavely

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Léopold Maillard , Tom Durand , Adrien Ramanana Rahary , Maks Ovsjanikov

Concept shift is a prevailing problem in natural tasks like medical image segmentation where samples usually come from different subpopulations with variant correlations between features and labels. One common type of concept shift in…

计算机视觉与模式识别 · 计算机科学 2023-02-01 Yijun Dong , Yuege Xie , Rachel Ward

Image composition in image editing involves merging a foreground image with a background image to create a composite. Inconsistent lighting conditions between the foreground and background often result in unrealistic composites. Image…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Jiajie Li , Jian Wang , Chen Wang , Jinjun Xiong

Street scene understanding is an essential task for autonomous driving. One important step towards this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been…

计算机视觉与模式识别 · 计算机科学 2019-05-07 Qi Wang , Junyu Gao , Yuan Yuan

Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. Recently, various lightweight learning-based LLIE methods have been proposed to handle the challenges of unfavorable prevailing…

计算机视觉与模式识别 · 计算机科学 2023-05-24 Yuantong Zhang , Baoxin Teng , Daiqin Yang , Zhenzhong Chen , Haichuan Ma , Gang Li , Wenpeng Ding

We present a scheme for fast environment light estimation from the RGBD appearance of individual objects and their local image areas. Conventional inverse rendering is too computationally demanding for real-time applications, and the…

计算机视觉与模式识别 · 计算机科学 2020-08-07 Xin Wei , Guojun Chen , Yue Dong , Stephen Lin , Xin Tong

Imbalanced data poses a significant challenge in classification as model performance is affected by insufficient learning from minority classes. Balancing methods are often used to address this problem. However, such techniques can lead to…

机器学习 · 计算机科学 2024-06-18 Adrian Stando , Mustafa Cavus , Przemysław Biecek

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g.,…

计算机视觉与模式识别 · 计算机科学 2018-03-23 Xuanyi Dong , Yan Yan , Wanli Ouyang , Yi Yang

Automatic color enhancement is aimed to adaptively adjust photos to expected styles and tones. For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model…

计算机视觉与模式识别 · 计算机科学 2019-07-23 Chaowei Shan , Zhizheng Zhang , Zhibo Chen

Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic…

计算机视觉与模式识别 · 计算机科学 2022-04-25 Bo Xu , Jiake Xie , Han Huang , Ziwen Li , Cheng Lu , Yong Tang , Yandong Guo

The perception of color is one of the most important aspects of human vision. From an evolutionary perspective, the accurate perception of color is crucial to distinguishing friend from foe, and food from fatal poison. As a result, humans…

图像与视频处理 · 电气工程与系统科学 2023-04-24 Abhinau K. Venkataramanan

Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Shay Shomer-Chai , Wenxuan Peng , Bharath Hariharan , Hadar Averbuch-Elor

Style-guided text image generation tries to synthesize text image by imitating reference image's appearance while keeping text content unaltered. The text image appearance includes many aspects. In this paper, we focus on transferring style…

计算机视觉与模式识别 · 计算机科学 2022-03-16 Yangming Shi , Haisong Ding , Kai Chen , Qiang Huo