中文
相关论文

相关论文: Anchoring and Rescaling Attention for Semantically…

200 篇论文

Generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input. Although remarkable progress has been made in video generation models, generative inbetweening still faces challenges in maintaining…

计算机视觉与模式识别 · 计算机科学 2024-12-17 Tianyi Zhu , Dongwei Ren , Qilong Wang , Xiaohe Wu , Wangmeng Zuo

Semantic segmentation is a fundamental problem in computer vision and it requires high-resolution feature maps for dense prediction. Current coordinate-guided low-resolution feature interpolation methods, e.g., bilinear interpolation,…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Tianheng Cheng , Xinggang Wang , Junchao Liao , Wenyu Liu

Keyframes are a standard representation for kinematic motion specification. Recent learned motion-inbetweening methods use keyframes as a way to control generative motion models, and are trained to generate life-like motion that matches the…

图形学 · 计算机科学 2025-03-04 Purvi Goel , Haotian Zhang , C. Karen Liu , Kayvon Fatahalian

Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving…

We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Xiaojuan Wang , Boyang Zhou , Brian Curless , Ira Kemelmacher-Shlizerman , Aleksander Holynski , Steven M. Seitz

Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Hao Zou , Runqing Zhang , Xue Zhou , Jianxiao Zou

Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions. However, these models cannot be directly applied on image/video…

计算机视觉与模式识别 · 计算机科学 2017-11-20 Avisek Lahiri , Arnav Jain , Prabir Kumar Biswas , Pabitra Mitra

Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…

计算机视觉与模式识别 · 计算机科学 2017-12-22 Haofeng Li , Guanbin Li , Liang Lin , Yizhou Yu

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods that first pretrain an…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Yibin Liu , Jianyu Zhang , Li Zhang , Shijian Li , Gang Pan

Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive…

计算机视觉与模式识别 · 计算机科学 2020-08-07 Yu Cheng , Zhe Gan , Yitong Li , Jingjing Liu , Jianfeng Gao

Autoregressive (AR) models based on next-scale prediction are rapidly emerging as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Ky Dan Nguyen , Hoang Lam Tran , Anh-Dung Dinh , Daochang Liu , Weidong Cai , Xiuying Wang , Chang Xu

In this paper, we propose StructInbet, an inbetweening system designed to generate controllable transitions over explicit structural guidance. StructInbet introduces two key contributions. First, we propose explicit structural guidance to…

图形学 · 计算机科学 2025-07-21 Zhenglin Pan , Haoran Xie

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an…

计算机视觉与模式识别 · 计算机科学 2022-03-25 Kai Hu , Wentong Liao , Michael Ying Yang , Bodo Rosenhahn

Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Jihyeon Kim , Sohee Kim , Soosan Lee , Souhwan Jung , James Matthew Rehg , Hyesong Choi

The rapid advancement of generative AI has revolutionized image creation, enabling high-quality synthesis from text prompts while raising critical challenges for media authenticity. We present Ai-GenBench, a novel benchmark designed to…

计算机视觉与模式识别 · 计算机科学 2025-12-17 Lorenzo Pellegrini , Davide Cozzolino , Serafino Pandolfini , Davide Maltoni , Matteo Ferrara , Luisa Verdoliva , Marco Prati , Marco Ramilli

The rapid development of generative artificial intelligence (AI) has introduced significant opportunities for enhancing the efficiency and accuracy of image transmission within semantic communication systems. Despite these advancements,…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Qiyu Ma , Wanli Ni , Zhijin Qin

Large-scale text-guided image diffusion models have shown astonishing results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Jiawei Lu , Yingpeng Zhang , Zengjun Zhao , He Wang , Kun Zhou , Tianjia Shao

Generative AI models perturb the foundations of effective human communication. They present new challenges to contextual confidence, disrupting participants' ability to identify the authentic context of communication and their ability to…

人工智能 · 计算机科学 2024-01-26 Shrey Jain , Zoë Hitzig , Pamela Mishkin

Generative adversarial networks (GANs) have demonstrated impressive image generation quality and semantic editing capability of real images, e.g., changing object classes, modifying attributes, or transferring styles. However, applying…

计算机视觉与模式识别 · 计算机科学 2022-06-22 Yiran Xu , Badour AlBahar , Jia-Bin Huang

Motion in-betweening, a fundamental task in character animation, consists of generating motion sequences that plausibly interpolate user-provided keyframe constraints. It has long been recognized as a labor-intensive and challenging…

计算机视觉与模式识别 · 计算机科学 2024-05-27 Setareh Cohan , Guy Tevet , Daniele Reda , Xue Bin Peng , Michiel van de Panne
‹ 上一页 1 2 3 10 下一页 ›