paper-with-me

Papers

Markup-to-Image Diffusion Models with Scheduled Sampling

2022-10-11 · Yuntian Deng, Noriyuki Kojima, Alexander M. Rush

Building on recent advances in image generation, we present a fully data-driven approach to rendering markup into images. The approach is based on diffusion models, which parameterize the distribution of data using a sequence of denoising operations on top of a Gaussian noise distribution. We view the diffusion denoising process as a sequential decision making process, and show that it exhibits compounding errors similar to exposure bias issues in imitation learning problems. To mitigate these issues, we adapt the scheduled sampling algorithm to diffusion training. We conduct experiments on four markup datasets: mathematical formulas (LaTeX), table layouts (HTML), sheet music (LilyPond), and molecular images (SMILES). These experiments each verify the effectiveness of the diffusion process and the use of scheduled sampling to fix generation issues. These results also show that the markup-to-image task presents a useful controlled compositional setting for diagnosing and analyzing generative image models.

📄 PDF Abstract BibTeX arXiv:2210.05147

Code (1)

da03/markup2im 공식 구현 pytorch

Tasks

Decision MakingDenoisingImage GenerationImitation LearningSequential Decision Making

Methods 이 논문이 사용한 방법론

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

Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation

2023-08-02 · Guojin Zhong, Jin Yuan, Pan Wang, Kailun Yang 외

The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup…

cross-modal alignmentDenoisingImage Generation

Sparse Scheduled Diffusion Guidance for Inverse Problems

2026-03-09 · Abduragim Shtanchaev, Albina Ilina, Yazid Janati, Arip Asadulaev 외 arxiv

Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because data-consistency guidance is applied throughout the full reverse trajectory…

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling

2023-10-26 · Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges 외

While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optim…

AttributeDiversityImage Generation

Parallel Scheduled Sampling

2019-06-11 · Daniel Duckworth, Arvind Neelakantan, Ben Goodrich, Lukasz Kaiser 외

Auto-regressive models are widely used in sequence generation problems. The output sequence is typically generated in a predetermined order, one discrete unit (pixel or word or character) at a time. The models are traine…

Image GenerationResponse Generation

F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion models

2025-09-30 · Zilai Li, Lujia Bai arxiv

Diffusion models are the state-of-the-art generative models for high-resolution images, but sampling from pretrained models is computationally expensive, motivating interest in fast sampling. Although Free-U Net is a tra…