中文
相关论文

相关论文: Science-T2I: Addressing Scientific Illusions in Im…

200 篇论文

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Yibin Wang , Zhimin Li , Yuhang Zang , Jiazi Bu , Yujie Zhou , Yi Xin , Junjun He , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Shantanu Jaiswal , Mihir Prabhudesai , Nikash Bhardwaj , Zheyang Qin , Amir Zadeh , Chuan Li , Katerina Fragkiadaki , Deepak Pathak

Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliability in knowledge-intensive settings remains largely unexplored. Unlike natural image…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Ran Zhao , Sheng Jin , Size Wu , Kang Liao , Zerui Gong , Zujin Guo , Yang Xiao , Wei Li

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Muxi Chen , Yi Liu , Jian Yi , Changran Xu , Qiuxia Lai , Hongliang Wang , Tsung-Yi Ho , Qiang Xu

Text to image generation methods (T2I) are widely popular in generating art and other creative artifacts. While visual hallucinations can be a positive factor in scenarios where creativity is appreciated, such artifacts are poorly suited…

计算机视觉与模式识别 · 计算机科学 2023-05-30 Rodrigo Valerio , Joao Bordalo , Michal Yarom , Yonatan Bitton , Idan Szpektor , Joao Magalhaes

Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Ying Ba , Tianyu Zhang , Yalong Bai , Wenyi Mo , Tao Liang , Bing Su , Ji-Rong Wen

With the rapid advancement of large multimodal models (LMMs), recent text-to-image (T2I) models can generate high-quality images and demonstrate great alignment to short prompts. However, they still struggle to effectively understand and…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Juntong Wang , Huiyu Duan , Jiarui Wang , Ziheng Jia , Guangtao Zhai , Xiongkuo Min

The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images…

计算机视觉与模式识别 · 计算机科学 2024-01-04 Paul Grimal , Hervé Le Borgne , Olivier Ferret , Julien Tourille

Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations,…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Jingjing Chang , Yixiao Fang , Peng Xing , Shuhan Wu , Wei Cheng , Rui Wang , Xianfang Zeng , Gang Yu , Hai-Bao Chen

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Haosheng Gan , Berk Tinaz , Mohammad Shahab Sepehri , Zalan Fabian , Mahdi Soltanolkotabi

Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Juekai Lin , Yun Zhu , Honglin Lin , Sijing Li , Tianwei Lin , Zheng Liu , Xiaoyang Wang , Wenqiao Zhang , Lijun Wu

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified prompts, leading to suboptimal image-text alignment, aesthetics, and quality. We propose a…

计算与语言 · 计算机科学 2025-10-16 Ruibo Chen , Jiacheng Pan , Heng Huang , Zhenheng Yang

Recently, text-to-image (T2I) synthesis has undergone significant advancements, particularly with the emergence of Large Language Models (LLM) and their enhancement in Large Vision Models (LVM), greatly enhancing the instruction-following…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Weijin Cheng , Jianzhi Liu , Jiawen Deng , Fuji Ren

Evaluating the quality of synthesized images remains a significant challenge in the development of text-to-image (T2I) generation. Most existing studies in this area primarily focus on evaluating text-image alignment, image quality, and…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Ziwei Huang , Wanggui He , Quanyu Long , Yandi Wang , Haoyuan Li , Zhelun Yu , Fangxun Shu , Long Chan , Hao Jiang , Fei Wu , Leilei Gan

Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Sedat Porikli , Vedat Porikli

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

计算与语言 · 计算机科学 2023-11-14 Tingfeng Cao , Chengyu Wang , Bingyan Liu , Ziheng Wu , Jinhui Zhu , Jun Huang

Translating information between text and image is a fundamental problem in artificial intelligence that connects natural language processing and computer vision. In the past few years, performance in image caption generation has seen…

计算机视觉与模式识别 · 计算机科学 2017-06-06 Hao Dong , Jingqing Zhang , Douglas McIlwraith , Yike Guo

The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Yichen Sun , Zhixuan Chu , Zhan Qin , Kui Ren

Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic…

Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Xiaoying Xing , Avinab Saha , Junfeng He , Susan Hao , Paul Vicol , Moonkyung Ryu , Gang Li , Sahil Singla , Sarah Young , Yinxiao Li , Feng Yang , Deepak Ramachandran