English
Related papers

Related papers: LooseRoPE: Content-aware Attention Manipulation fo…

200 papers

Recent advancements in diffusion models have significantly broadened the possibilities for editing images of real-world objects. However, performing non-rigid transformations, such as changing the pose of objects or image-based…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Potito Aghilar , Vito Walter Anelli , Michelantonio Trizio , Tommaso Di Noia

Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Qiucheng Wu , Yujian Liu , Handong Zhao , Trung Bui , Zhe Lin , Yang Zhang , Shiyu Chang

Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts, their guiding principles generally fall into two…

Computation and Language · Computer Science 2026-02-06 Haoran Li , Sucheng Ren , Alan Yuille , Feng Wang

Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yuxi Liu , Zekun Zhang , Yixiang Cai , Renjia Deng , Yutong He , Kun Yuan

We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Eyal Gomel , Lior Wolf

Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Pengzhi Li , Qiang Nie , Ying Chen , Xi Jiang , Kai Wu , Yuhuan Lin , Yong Liu , Jinlong Peng , Chengjie Wang , Feng Zheng

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Yunji Kim , Jiyoung Lee , Jin-Hwa Kim , Jung-Woo Ha , Jun-Yan Zhu

Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Wan-Duo Kurt Ma , J. P. Lewis , Avisek Lahiri , Thomas Leung , W. Bastiaan Kleijn

Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts. Based on the T2I diffusion models, text-guided image editing research aims to empower users to manipulate generated…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Chuanming Tang , Kai Wang , Fei Yang , Joost van de Weijer

Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Haoyang Hu , Masataka Seo , Yen-Wei Chen

Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations, while in linear transformers, order is handled via…

Computation and Language · Computer Science 2026-04-27 Sajad Movahedi , Timur Carstensen , Arshia Afzal , Frank Hutter , Antonio Orvieto , Volkan Cevher

Diffusion-model-based text-guided image generation has recently made astounding progress, producing fascinating results in open-domain image manipulation tasks. Few models, however, currently have complete zero-shot capabilities for both…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Sijia Li , Chen Chen , Haonan Lu

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Pengzhi Li , QInxuan Huang , Yikang Ding , Zhiheng Li

Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images. However, existing models are limited by the quality of the dataset and cannot accurately localize editing…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Tiancheng Li , Jinxiu Liu , Huajun Chen , Qi Liu

Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Siyi Chen , Huijie Zhang , Minzhe Guo , Yifu Lu , Peng Wang , Qing Qu

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Youngrae Kim , Qixin Hu , C. -C. Jay Kuo , Peter A. Beerel

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Machine Learning · Computer Science 2026-05-12 Riccardo Ali , Alessio Borgi , Christopher Irwin , Mario Severino , Pietro Liò

Despite the great success of large-scale text-to-image diffusion models in image generation and image editing, existing methods still struggle to edit the layout of real images. Although a few works have been proposed to tackle this…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Tao Xia , Yudi Zhang , Ting Liu Lei Zhang

We propose a diffusion-based approach for Text-to-Image (T2I) generation with consistent and interactive 3D layout control and editing. While prior methods improve spatial adherence using 2D cues or iterative copy-warp-paste strategies,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Andrea Rigo , Luca Stornaiuolo , Weijie Wang , Mauro Martino , Bruno Lepri , Nicu Sebe

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows $SE(3)$-invariant attention with multi-frequency similarity, and can…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yu Wu , Minsik Jeon , Jen-Hao Rick Chang , Oncel Tuzel , Shubham Tulsiani