English
Related papers

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

200 papers

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Omri Avrahami , Or Patashnik , Ohad Fried , Egor Nemchinov , Kfir Aberman , Dani Lischinski , Daniel Cohen-Or

Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…

Machine Learning · Computer Science 2025-05-22 Nanxu Gong , Zijun Li , Sixun Dong , Haoyue Bai , Wangyang Ying , Xinyuan Wang , Yanjie Fu

Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Zhichao Wei , Qingkun Su , Long Qin , Weizhi Wang

To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable. Recently, Drag-based editing methods have gained impressive performance. However, these methods predominantly…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Pengyang Ling , Lin Chen , Pan Zhang , Huaian Chen , Yi Jin , Jinjin Zheng

This paper proposes FreeFuse, a training-free framework for multi-subject text-to-image generation through automatic fusion of multiple subject LoRAs. In contrast to prior studies that focus on retraining LoRA to alleviate feature…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yaoli Liu , Yao-Xiang Ding , Kun Zhou

Text driven diffusion models have shown remarkable capabilities in editing images. However, when editing 3D scenes, existing works mostly rely on training a NeRF for 3D editing. Recent NeRF editing methods leverages edit operations by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Vivek Madhavaram , Shivangana Rawat , Chaitanya Devaguptapu , Charu Sharma , Manohar Kaul

We identify a core failure mode that occurs when using the usual linear interpolation on rotary positional embeddings (RoPE) for mixed-resolution denoising with Diffusion Transformers. When tokens from different spatial grids are mixed, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Haoyu Wu , Jingyi Xu , Qiaomu Miao , Dimitris Samaras , Hieu Le

We study training-free image editing on Qwen-Image-Edit-2511, a 60-block multi-modal diffusion transformer (MMDiT) that concatenates noise and source-image tokens within a single attention stream. We make three contributions. (i) We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Guandong Li , Mengxia Ye

Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to support multilingual generation. In this work, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yu Xie , Jielei Zhang , Pengyu Chen , Weihang Wang , Longwen Gao , Peiyi Li , Qian Qiao , Zhouhui Lian

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE), such as RoPE, need extrapolating to unseen positions which…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Shen Zhang , Siyuan Liang , Yaning Tan , Zhaowei Chen , Linze Li , Ge Wu , Yuhao Chen , Shuheng Li , Zhenyu Zhao , Caihua Chen , Jiajun Liang , Yao Tang

Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domains have been underexplored, even though RoPE appears capable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Byeongho Heo , Song Park , Dongyoon Han , Sangdoo Yun

Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on vector-level split and merge operations that introduce…

Machine Learning · Computer Science 2026-04-14 Chen Minqi , Zhongqi Yue , Shihao Zhang , Yun Xu , Peng Wu , kaixiang Xu , Zeyi Huang , Hanwang Zhang

Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jiaye Li , Baoyou Chen , Hui Li , Zilong Dong , Jingdong Wang , Siyu Zhu

Image-conditioned generation methods, such as depth- and canny-conditioned approaches, have demonstrated remarkable abilities for precise image synthesis. However, existing models still struggle to accurately control the content of multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Dewei Zhou , Mingwei Li , Zongxin Yang , Yi Yang

Diffusion Magnetic Resonance Imaging (dMRI) plays a critical role in studying microstructural changes in the brain. It is, therefore, widely used in clinical practice; yet progress in learning general-purpose representations from dMRI has…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Gustavo Chau Loo Kung , Mohammad Abbasi , Camila Blank , Juze Zhang , Alan Q. Wang , Sophie Ostmeier , Akshay Chaudhari , Kilian Pohl , Ehsan Adeli

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…

Robotics · Computer Science 2025-03-20 Jianbo Zhao , Taiyu Ban , Zhihao Liu , Hangning Zhou , Xiyang Wang , Qibin Zhou , Hailong Qin , Mu Yang , Lei Liu , Bin Li

The growing demand for controllable outputs in text-to-image generation has driven significant advancements in multi-instance generation (MIG), enabling users to define both instance layouts and attributes. Currently, the state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Dewei Zhou , Ji Xie , Zongxin Yang , Yi Yang

Painting textures for existing geometries is a critical yet labor-intensive process in 3D asset generation. Recent advancements in text-to-image (T2I) models have led to significant progress in texture generation. Most existing research…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Yifei Feng , Mingxin Yang , Shuhui Yang , Sheng Zhang , Jiaao Yu , Zibo Zhao , Yuhong Liu , Jie Jiang , Chunchao Guo

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Enis Simsar , Alessio Tonioni , Yongqin Xian , Thomas Hofmann , Federico Tombari

Generative models have made remarkable advancements and are capable of producing high-quality content. However, performing controllable editing with generative models remains challenging, due to their inherent uncertainty in outputs. This…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Yikun Ma , Yiqing Li , Jiawei Wu , Xing Luo , Zhi Jin