English
Related papers

Related papers: FreeFlux: Understanding and Exploiting Layer-Speci…

200 papers

This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Zipeng Qi , Guoxi Huang , Chenyang Liu , Fei Ye

Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Vladimir Kulikov , Matan Kleiner , Inbar Huberman-Spiegelglas , Tomer Michaeli

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Zihan Zhou , Shilin Lu , Shuli Leng , Shaocong Zhang , Zhuming Lian , Xinlei Yu , Adams Wai-Kin Kong

Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pre-trained video models using camera poses relative to a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Chunyang Li , Yuanbo Yang , Jiahao Shao , Hongyu Zhou , Katja Schwarz , Yiyi Liao

The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-23 Runyi Yu , Zhennan Wang , Yinhuai Wang , Kehan Li , Yian Zhao , Jian Zhang , Guoli Song , Jie Chen

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yiqing Shi , Yiren Song , Mike Zheng Shou

Text-to-Image (T2I) generation models have advanced rapidly in recent years, but accurately capturing spatial relationships like "above" or "to the right of" poses a persistent challenge. Earlier methods improved spatial relationship…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jessica Bader , Mateusz Pach , Maria A. Bravo , Serge Belongie , Zeynep Akata

Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret…

Machine Learning · Computer Science 2026-02-12 Feilong Liu

Accurate spatial correspondence between medical images is essential for longitudinal analysis, lesion tracking, and image-guided interventions. Medical image registration methods rely on local intensity-based similarity measures, which fail…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xingyu Zhang , Anna Reithmeir , Fryderyk Kögl , Rickmer Braren , Julia A. Schnabel , Daniel M. Lang

Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography, and long-tailed scripts such as Chinese. Prior solutions…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Ruiqiang Zhang , Hengyi Wang , Chang Liu , Guanjie Wang , Zehua Ma , Weiming Zhang

Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental "granularity dilemma": capturing global semantics favors large patch scales, while generating high-fidelity details…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yu He , Lichen Ma , Zipeng Guo , Xinyuan Shan , Jingling Fu , Dong Chen , Junshi Huang , Yan Li

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

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

Image manipulation under the guidance of textual descriptions has recently received a broad range of attention. In this study, we focus on the regional editing of images with the guidance of given text prompts. Different from current…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Nisha Huang , Fan Tang , Weiming Dong , Tong-Yee Lee , Changsheng Xu

Image generation using diffusion can be controlled in multiple ways. In this paper, we systematically analyze the equations of modern generative diffusion networks to propose a framework, called MDP, that explains the design space of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Qian Wang , Biao Zhang , Michael Birsak , Peter Wonka

Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xincheng Shuai , Zhenyuan Qin , Henghui Ding , Dacheng Tao

In light of recent breakthroughs in text-to-image (T2I) generation, particularly with diffusion transformers (DiT), subject-driven technologies are increasingly being employed for high-fidelity customized production that preserves subject…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yanbing Zhang , Zhe Wang , Qin Zhou , Mengping Yang

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yuyao Zhang , Alexander Huang-Menders , Yu-Wing Tai

Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency…

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki