paper-with-me

Papers

T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalities

2023-05-24 · Kangfu Mei, Mo Zhou, Vishal M. Patel

Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. While DPF shows great potential for unifying data generation of various modalities including images, videos, and 3D geometry, it does not scale to a higher data resolution. This can be attributed to the ``scaling property'', where it is difficult for the model to capture local structures through uniform sampling. To this end, we propose a new model comprising of a view-wise sampling algorithm to focus on local structure learning, and incorporating additional guidance, e.g., text description, to complement the global geometry. The model can be scaled to generate high-resolution data while unifying multiple modalities. Experimental results on data generation in various modalities demonstrate the effectiveness of our model, as well as its potential as a foundation framework for scalable modality-unified visual content generation.

📄 PDF Abstract BibTeX arXiv:2305.14674

Code (0)

등록된 구현이 없습니다.

Tasks

3D geometry

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

2026-03-30 · Joffrey Dumont Le Brazidec, Simon Lang, Martin Leutbecher, Baudouin Raoult 외 arxiv

We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble forecasts into high-resolution ensembles by …

Km-scale dynamical downscaling through conformalized latent diffusion models

2025-10-15 · Alessandro Brusaferri, Andrea Ballarino arxiv

Dynamical downscaling is crucial for deriving high-resolution meteorological fields from coarse-scale simulations, enabling detailed analysis for critical applications such as weather forecasting and renewable energy mod…

Weather Forecasting

IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales

2026-03-23 · Kishanthan Kingston, Olivier Boucher, Freddy Bouchet, Pierre Chapel 외 arxiv

Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150…

Universal Diffusion-Based Probabilistic Downscaling

2026-02-12 · Roberto Molinaro, Niall Siegenheim, Henry Martin, Mark Frey 외 arxiv

We introduce a universal diffusion-based downscaling framework that lifts deterministic low-resolution weather forecasts into probabilistic high-resolution predictions without any model-specific fine-tuning. A single con…

Weather Forecasting

Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learning

2024-03-05 · Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers

Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at suff…