中文
相关论文

相关论文: Region-to-Region: Enhancing Generative Image Harmo…

200 篇论文

Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In…

计算机视觉与模式识别 · 计算机科学 2022-05-03 Xinyuan Lu , Shengyuan Huang , Li Niu , Wenyan Cong , Liqing Zhang

While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains. Some approaches address this issue by fine-tuning models in…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Jaa-Yeon Lee , Byunghee Cha , Jeongsol Kim , Jong Chul Ye

Real-image super-resolution (Real-ISR) seeks to recover HR images from LR inputs with mixed, unknown degradations. While diffusion models surpass GANs in perceptual quality, they under-reconstruct high-frequency (HF) details due to a…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Seungho Choi , Jeahun Sung , Jihyong Oh

In the field of computer vision, the persistent presence of color bias, resulting from fluctuations in real-world lighting and camera conditions, presents a substantial challenge to the robustness of models. This issue is particularly…

计算机视觉与模式识别 · 计算机科学 2024-01-22 Yunpeng Gong , Jiaquan Li , Lifei Chen , Min Jiang

We seek to give users precise control over diffusion-based image generation by modeling complex scenes as sequences of layers, which define the desired spatial arrangement and visual attributes of objects in the scene. Collage Diffusion…

计算机视觉与模式识别 · 计算机科学 2023-09-01 Vishnu Sarukkai , Linden Li , Arden Ma , Christopher Ré , Kayvon Fatahalian

We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught…

图像与视频处理 · 电气工程与系统科学 2026-02-03 Yan Chen , Yi Wen , Wei Li , Junchao Liu , Yong Guo , Jie Hu , Xinghao Chen

Combining neuroimaging datasets from multiple sites and scanners can help increase statistical power and thus provide greater insight into subtle neuroanatomical effects. However, site-specific effects pose a challenge by potentially…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Ayodeji Ijishakin , Ana Lawry Aguila , Elizabeth Levitis , Ahmed Abdulaal , Andre Altmann , James Cole

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…

图形学 · 计算机科学 2026-04-24 Etai Sella , Yoav Baron , Hadar Averbuch-Elor , Daniel Cohen-Or , Or Patashnik

Deployment of machine learning algorithms into real-world practice is still a difficult task. One of the challenges lies in the unpredictable variability of input data, which may differ significantly among individual users, institutions,…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Roman Stoklasa

Digital image inpainting is an interpolation problem, inferring the content in the missing (unknown) region to agree with the known region data such that the interpolated result fulfills some prior knowledge. Low-rank and nonlocal…

计算机视觉与模式识别 · 计算机科学 2023-03-23 Shenghai Liao , Xuya Liu , Ruyi Han , Shujun Fu , Yuanfeng Zhou , Yuliang Li

We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. Differently from prior works, we solve this problem by learning a conditional probability…

计算机视觉与模式识别 · 计算机科学 2022-05-04 Andrew Brown , Cheng-Yang Fu , Omkar Parkhi , Tamara L. Berg , Andrea Vedaldi

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Yunzhuo Chen , Jordan Vice , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

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

The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of…

计算机视觉与模式识别 · 计算机科学 2024-05-02 Zheng Zeng , Valentin Deschaintre , Iliyan Georgiev , Yannick Hold-Geoffroy , Yiwei Hu , Fujun Luan , Ling-Qi Yan , Miloš Hašan

Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Stanislav Frolov , Prateek Bansal , Jörn Hees , Andreas Dengel

Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…

计算机视觉与模式识别 · 计算机科学 2025-05-05 Daneul Kim , Jaeah Lee , Jaesik Park

Layout-to-Image generation aims to create complex scenes with precise control over the placement and arrangement of subjects. Existing works have demonstrated that pre-trained Text-to-Image diffusion models can achieve this goal without…

计算机视觉与模式识别 · 计算机科学 2025-06-19 Bonan Li , Yinhan Hu , Songhua Liu , Xinchao Wang

Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity,…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Gemma Canet Tarrés , Manel Baradad , Francesc Moreno-Noguer , Yumeng Li

Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model…

Recently, many text-to-image diffusion models have excelled at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works have…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Huancheng Chen , Jingtao Li , Weiming Zhuang , Haris Vikalo , Lingjuan Lyu