中文
相关论文

相关论文: VectorEdits: A Dataset and Benchmark for Instructi…

200 篇论文

Despite the advances in text-to-image synthesis, particularly with diffusion models, generating visual instructions that require consistent representation and smooth state transitions of objects across sequential steps remains a formidable…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Quynh Phung , Songwei Ge , Jia-Bin Huang

We consider the task of generating designs directly from natural language descriptions, and consider floor plan generation as the initial research area. Language conditional generative models have recently been very successful in generating…

计算与语言 · 计算机科学 2023-11-28 Sicong Leng , Yang Zhou , Mohammed Haroon Dupty , Wee Sun Lee , Sam Conrad Joyce , Wei Lu

Recent advancements in image editing have enabled highly controllable and semantically-aware alteration of visual content, posing unprecedented challenges to manipulation localization. However, existing AI-generated forgery localization…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Shiyu Wu , Shuyan Li , Jing Li , Jing Liu , Yequan Wang

Recent research in behaviour understanding through language grounding has shown it is possible to automatically generate behaviour models from textual instructions. These models usually have goal-oriented structure and are modelled with…

人工智能 · 计算机科学 2020-01-14 Debajyoti Paul Chowdhury , Arghya Biswas , Tomasz Sosnowski , Kristina Yordanova

Vector graphics are widely used to represent fonts, logos, digital artworks, and graphic designs. But, while a vast body of work has focused on generative algorithms for raster images, only a handful of options exists for vector graphics.…

计算机视觉与模式识别 · 计算机科学 2021-04-02 Pradyumna Reddy , Michael Gharbi , Michal Lukac , Niloy J. Mitra

Automatic image editing has great demands because of its numerous applications, and the use of natural language instructions is essential to achieving flexible and intuitive editing as the user imagines. A pioneering work in text-driven…

计算机视觉与模式识别 · 计算机科学 2023-04-04 Tsuyoshi Baba , Kosuke Nishida , Kyosuke Nishida

This paper focuses on understanding the predominant video creation pipeline, i.e., compositional video editing with six main types of editing components, including video effects, animation, transition, filter, sticker, and text. In contrast…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Xin Gu , Libo Zhang , Fan Chen , Longyin Wen , Yufei Wang , Tiejian Luo , Sijie Zhu

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Yaofang Liu , Xiaodong Cun , Xuebo Liu , Xintao Wang , Yong Zhang , Haoxin Chen , Yang Liu , Tieyong Zeng , Raymond Chan , Ying Shan

Generative models, such as diffusion and autoregressive approaches, have demonstrated impressive capabilities in editing natural images. However, applying these tools to scientific charts rests on a flawed assumption: a chart is not merely…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Shawn Li , Ryan Rossi , Sungchul Kim , Sunav Choudhary , Franck Dernoncourt , Puneet Mathur , Zhengzhong Tu , Yue Zhao

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor sufficient feedback…

人机交互 · 计算机科学 2024-08-14 Ruei-Che Chang , Yuxuan Liu , Lotus Zhang , Anhong Guo

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

计算机视觉与模式识别 · 计算机科学 2024-12-25 Changjian Chen , Fei Lv , Yalong Guan , Pengcheng Wang , Shengjie Yu , Yifan Zhang , Zhuo Tang

Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of…

计算机视觉与模式识别 · 计算机科学 2022-09-07 Katherine Crowson , Stella Biderman , Daniel Kornis , Dashiell Stander , Eric Hallahan , Louis Castricato , Edward Raff

Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the…

计算与语言 · 计算机科学 2020-10-15 Hao Tan , Mohit Bansal

Despite the rapid progress of instruction-based image editing, its extension to video remains underexplored, primarily due to the prohibitive cost and complexity of constructing large-scale paired video editing datasets. To address this…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Xinyao Liao , Xianfang Zeng , Ziye Song , Zhoujie Fu , Gang Yu , Guosheng Lin

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which…

计算机视觉与模式识别 · 计算机科学 2023-11-08 Manel Baradad , Chun-Fu Chen , Jonas Wulff , Tongzhou Wang , Rogerio Feris , Antonio Torralba , Phillip Isola

Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This…

计算与语言 · 计算机科学 2023-10-24 Gaurav Verma , Ryan A. Rossi , Christopher Tensmeyer , Jiuxiang Gu , Ani Nenkova

This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between real data and…

计算机视觉与模式识别 · 计算机科学 2024-12-23 Abdullah Al Rahat , Hemanth Venkateswara

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences,…

Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce…

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identifies an important…

计算机视觉与模式识别 · 计算机科学 2018-08-08 Rameswar Panda , Jianming Zhang , Haoxiang Li , Joon-Young Lee , Xin Lu , Amit K. Roy-Chowdhury