paper-with-me

Papers

Constrained Synthesis with Projected Diffusion Models

2024-02-05 · Jacob K Christopher, Stephen Baek, Ferdinando Fioretto

This paper introduces an approach to endow generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional sampling process of generative diffusion models as a constrained optimization problem, steering the generated data distribution to remain within a specified region to ensure adherence to the given constraints. These capabilities are validated on applications featuring both convex and challenging, non-convex, constraints as well as ordinary differential equations, in domains spanning from synthesizing new materials with precise morphometric properties, generating physics-informed motion, optimizing paths in planning scenarios, and human motion synthesis.

📄 PDF Abstract BibTeX arXiv:2402.03559

Code (1)

RAISELab-atUVA/Projected-Diffusion 공식 구현 pytorch

Tasks

Motion SynthesisVideo Generation

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

Projected Coupled Diffusion for Test-Time Constrained Joint Generation

2025-08-14 · Hao Luan, Yi Xian Goh, See-Kiong Ng, Chun Kai Ling arxiv

Modifications to test-time sampling have emerged as an important extension to diffusion algorithms, with the goal of biasing the generative process to achieve a given objective without having to retrain the entire diffus…

Motion Planning

Projected Representation Conditioning for High-fidelity Novel View Synthesis

2026-02-12 · Min-Seop Kwak, Minkyung Kwon, Jinhyeok Choi, Jiho Park 외 arxiv

We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspondence properties for enhanced geometric …

Semantic correspondenceNovel View Synthesis

Boosting Latent Diffusion with Flow Matching

2023-12-12 · Johannes Schusterbauer, Ming Gui, Pingchuan Ma, Nick Stracke 외

Visual synthesis has recently seen significant leaps in performance, largely due to breakthroughs in generative models. Diffusion models have been a key enabler, as they excel in image diversity. However, this comes at t…

DecoderDiversityImage Generation

Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion

2023-01-01 · ICCV 2023 1 · Xiao Han, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song 외

Controllable person image synthesis aims at rendering a source image based on user-specified changes in body pose or appearance. Prior art approaches leverage pixel-level denoising diffusion models conditioned on the…

DenoisingImage Generation

Constrained Diffusers for Safe Planning and Control

2025-06-14 · Jichen Zhang, Liqun Zhao, Antonis Papachristodoulou, Jack Umenberger

Diffusion models have shown remarkable potential in planning and control tasks due to their ability to represent multimodal distributions over actions and trajectories. However, ensuring safety under constraints remains …