English
Related papers

Related papers: Improving Compositional Generation with Diffusion …

200 papers

In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Brinnae Bent

Modern generative models exhibit unprecedented capabilities to generate extremely realistic data. However, given the inherent compositionality of the real world, reliable use of these models in practical applications requires that they…

Machine Learning · Computer Science 2025-07-29 Maya Okawa , Ekdeep Singh Lubana , Robert P. Dick , Hidenori Tanaka

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Shantanu Jaiswal , Mihir Prabhudesai , Nikash Bhardwaj , Zheyang Qin , Amir Zadeh , Chuan Li , Katerina Fragkiadaki , Deepak Pathak

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…

Machine Learning · Computer Science 2025-05-22 Tianyu Chen , Yasi Zhang , Zhendong Wang , Ying Nian Wu , Oscar Leong , Mingyuan Zhou

Generative diffusion models synthesize new samples by reversing a diffusive process that converts a given data set to generic noise. This is accomplished by training a neural network to match the gradient of the log of the probability…

Machine Learning · Computer Science 2023-10-11 Akhil Premkumar

Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Jeongsol Kim , Geon Yeong Park , Jong Chul Ye

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

Computer Vision and Pattern Recognition · Computer Science 2023-02-17 Ye Zhu , Yu Wu , Kyle Olszewski , Jian Ren , Sergey Tulyakov , Yan Yan

Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Yujin Jeong , Arnas Uselis , Seong Joon Oh , Anna Rohrbach

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Sound · Computer Science 2024-10-31 Javier Nistal , Marco Pasini , Stefan Lattner

Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements…

Image and Video Processing · Electrical Eng. & Systems 2024-08-07 Hongjie Wu , Linchao He , Mingqin Zhang , Dongdong Chen , Kunming Luo , Mengting Luo , Ji-Zhe Zhou , Hu Chen , Jiancheng Lv

Text-to-3D generation has achieved significant success by incorporating powerful 2D diffusion models, but insufficient 3D prior knowledge also leads to the inconsistency of 3D geometry. Recently, since large-scale multi-view datasets have…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Junyoung Seo , Susung Hong , Wooseok Jang , Inès Hyeonsu Kim , Minseop Kwak , Doyup Lee , Seungryong Kim

Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Yudong Yang , Zhan Liu , Wenyi Yu , Guangzhi Sun , Qiuqiang Kong , Chao Zhang

State-of-the-art T2I models are capable of generating high-resolution images given textual prompts. However, they still struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Yixin Wan , Kai-Wei Chang

Diffusion models have shown great promise in synthesizing visually appealing images. However, it remains challenging to condition the synthesis at a fine-grained level, for instance, synthesizing image pixels following some generic color…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ka Chun Shum , Binh-Son Hua , Duc Thanh Nguyen , Sai-Kit Yeung

Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Luozhou Wang , Guibao Shen , Wenhang Ge , Guangyong Chen , Yijun Li , Ying-cong Chen

Score-based generative models (SGMs) have demonstrated remarkable synthesis quality. SGMs rely on a diffusion process that gradually perturbs the data towards a tractable distribution, while the generative model learns to denoise. The…

Machine Learning · Statistics 2022-03-28 Tim Dockhorn , Arash Vahdat , Karsten Kreis

Generating multi-instrument music from symbolic music representations is an important task in Music Information Retrieval (MIR). A central but still largely unsolved problem in this context is musically and acoustically informed control in…

Sound · Computer Science 2023-09-22 Ben Maman , Johannes Zeitler , Meinard Müller , Amit H. Bermano

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mapping noise to data,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Shelly Golan , Roy Ganz , Michael Elad

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

Computation and Language · Computer Science 2023-11-14 Tingfeng Cao , Chengyu Wang , Bingyan Liu , Ziheng Wu , Jinhui Zhu , Jun Huang

Despite their impressive realism, modern text-to-image models still struggle with compositionality, often failing to render accurate object counts, attributes, and spatial relations. To address this challenge, we present a training-free…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Minsuk Ji , Sanghyeok Lee , Namhyuk Ahn