中文
相关论文

相关论文: CLPIPS: A Personalized Metric for AI-Generated Ima…

200 篇论文

Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself remains an underexplored factor in this process. We revisit…

In most practical situations, the compression or transmission of images and videos creates distortions that will eventually be perceived by a human observer. Vice versa, image and video restoration techniques, such as inpainting or…

计算机视觉与模式识别 · 计算机科学 2017-11-29 Rafael Reisenhofer , Sebastian Bosse , Gitta Kutyniok , Thomas Wiegand

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Konstantin Schall , Kai Uwe Barthel , Nico Hezel , Klaus Jung

The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics…

计算机视觉与模式识别 · 计算机科学 2024-10-11 Zhiyu Tan , Xiaomeng Yang , Luozheng Qin , Mengping Yang , Cheng Zhang , Hao Li

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Bowen Qu , Shangkun Sun , Xiaoyu Liang , Wei Gao

Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive…

人工智能 · 计算机科学 2024-04-09 Shachar Rosenman , Vasudev Lal , Phillip Howard

Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Amit Zalcher , Navve Wasserman , Roman Beliy , Oliver Heinimann , Michal Irani

Text-to-image generation has advanced rapidly, yet aligning complex textual prompts with generated visuals remains challenging, especially with intricate object relationships and fine-grained details. This paper introduces Fast Prompt…

计算与语言 · 计算机科学 2024-12-12 Khalil Mrini , Hanlin Lu , Linjie Yang , Weilin Huang , Heng Wang

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Guocheng Gordon Qian , Daniil Ostashev , Egor Nemchinov , Avihay Assouline , Sergey Tulyakov , Kuan-Chieh Jackson Wang , Kfir Aberman

Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Sixian Zhang , Bohan Wang , Junqiang Wu , Yan Li , Tingting Gao , Di Zhang , Zhongyuan Wang

Personalizing text-to-image models using a limited set of images for a specific object has been explored in subject-specific image generation. However, existing methods often face challenges in aligning with text prompts due to overfitting…

计算机视觉与模式识别 · 计算机科学 2024-02-16 Daewon Chae , Nokyung Park , Jinkyu Kim , Kimin Lee

Recent breakthroughs in large multimodal models (LMMs) have significantly advanced both text-to-image (T2I) generation and image-to-text (I2T) interpretation. However, many generated images still suffer from issues related to perceptual…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Jiarui Wang , Huiyu Duan , Yu Zhao , Juntong Wang , Guangtao Zhai , Xiongkuo Min

Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences. To produce beautiful composites, the camera needs to be geometrically calibrated, which can be tedious and requires a physical…

Recent advances in image editing have shifted from manual pixel manipulation to employing deep learning methods like stable diffusion models, which now leverage cross-attention mechanisms for text-driven control. This transition has…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Linn Bieske , Carla Lorente

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

计算与语言 · 计算机科学 2025-06-16 Víctor Gallego

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

计算与语言 · 计算机科学 2024-01-01 Yaru Hao , Zewen Chi , Li Dong , Furu Wei

The advent of text-image models, most notably CLIP, has significantly transformed the landscape of information retrieval. These models enable the fusion of various modalities, such as text and images. One significant outcome of CLIP is its…

Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across various contexts. However, current evaluations either are…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Yuang Peng , Yuxin Cui , Haomiao Tang , Zekun Qi , Runpei Dong , Jing Bai , Chunrui Han , Zheng Ge , Xiangyu Zhang , Shu-Tao Xia

Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generation remains underexplored, despite its critical role in…

计算与语言 · 计算机科学 2026-05-28 Zhipeng Bian , Jieming Zhu , Qijiong Liu , Wang Lin , Guohao Cai , Zhaocheng Du , Jiacheng Sun , Zhou Zhao , Zhenhua Dong

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Hongji Yang , Yucheng Zhou , Wencheng Han , Jianbing Shen