paper-with-me

Papers

Compositional Image Decomposition with Diffusion Models

2024-06-27 · Jocelin Su, Nan Liu, Yanbo Wang, Joshua B. Tenenbaum, Yilun Du

Given an image of a natural scene, we are able to quickly decompose it into a set of components such as objects, lighting, shadows, and foreground. We can then envision a scene where we combine certain components with those from other images, for instance a set of objects from our bedroom and animals from a zoo under the lighting conditions of a forest, even if we have never encountered such a scene before. In this paper, we present a method to decompose an image into such compositional components. Our approach, Decomp Diffusion, is an unsupervised method which, when given a single image, infers a set of different components in the image, each represented by a diffusion model. We demonstrate how components can capture different factors of the scene, ranging from global scene descriptors like shadows or facial expression to local scene descriptors like constituent objects. We further illustrate how inferred factors can be flexibly composed, even with factors inferred from other models, to generate a variety of scenes sharply different than those seen in training time. Website and code at https://energy-based-model.github.io/decomp-diffusion.

📄 PDF Abstract BibTeX arXiv:2406.19298

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models

2025-12-26 · Jianrong Zhang, Hehe Fan, Yi Yang arxiv

Human motions are compositional: complex behaviors can be described as combinations of simpler primitives. However, existing approaches primarily focus on forward modeling, e.g., learning holistic mappings from text to m…

Interpretable Diffusion via Information Decomposition

2023-10-12 · Xianghao Kong, Ollie Liu, Han Li, Dani Yogatama 외

Denoising diffusion models enable conditional generation and density modeling of complex relationships like images and text. However, the nature of the learned relationships is opaque making it difficult to understand pr…

Image GenerationVision-Language Segmentation

OmniPSD: Layered PSD Generation with Diffusion Transformer

2025-12-10 · Cheng Liu, Yiren Song, Haofan Wang, Mike Zheng Shou arxiv

Recent advances in diffusion models have greatly improved image generation and editing, yet generating or reconstructing layered PSD files with transparent alpha channels remains highly challenging. We propose OmniPSD, a…

Image Generation

Factorized Diffusion: Perceptual Illusions by Noise Decomposition

2024-04-17 · Daniel Geng, Inbum Park, Andrew Owens

Given a factorization of an image into a sum of linear components, we present a zero-shot method to control each individual component through diffusion model sampling. For example, we can decompose an image into low and …

Denoising

A Two-Stage System for Layout-Controlled Image Generation using Large Language Models and Diffusion Models

2025-11-10 · Jan-Hendrik Koch, Jonas Krumme, Konrad Gadzicki arxiv

Text-to-image diffusion models exhibit remarkable generative capabilities, but lack precise control over object counts and spatial arrangements. This work introduces a two-stage system to address these compositional limi…

Image Generation