Image de couverture de livre

Elucidating the solution space of extended reverse-time SDE for diffusion models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cui, Qinpeng, Zhang, Xinyi, Bao, Qiqi, Liao, Qingmin
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
par: Zhang, Xinyi, et autres
Publié: (2024)

Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
par: Cui, Qinpeng, et autres
Publié: (2024)

Secure and reversible face anonymization with diffusion models
par: Labarbarie, Pol, et autres
Publié: (2025)

Elucidating the Preconditioning in Consistency Distillation
par: Zheng, Kaiwen, et autres
Publié: (2025)

The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing
par: Nie, Shen, et autres
Publié: (2023)

SyncSDE: A Probabilistic Framework for Diffusion Synchronization
par: Lee, Hyunjun, et autres
Publié: (2025)

DFU: scale-robust diffusion model for zero-shot super-resolution image generation
par: Havrilla, Alex, et autres
Publié: (2023)

Explore the vulnerability of black-box models via diffusion models
par: Shi, Jiacheng, et autres
Publié: (2025)

WaveDiffUR: A diffusion SDE-based solver for ultra magnification super-resolution in remote sensing images
par: Shi, Yue, et autres
Publié: (2024)

An attempt to generate new bridge types from latent space of denoising diffusion Implicit model
par: Zhang, Hongjun
Publié: (2024)

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
par: Park, Yonghyun, et autres
Publié: (2025)

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
par: Zou, Jade, et autres
Publié: (2026)

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
par: Qiu, Xingyu, et autres
Publié: (2025)

Fast constrained sampling in pre-trained diffusion models
par: Graikos, Alexandros, et autres
Publié: (2024)

FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
par: Neukirch, Nils, et autres
Publié: (2025)

Blue noise for diffusion models
par: Huang, Xingchang, et autres
Publié: (2024)

Amortizing intractable inference in diffusion models for vision, language, and control
par: Venkatraman, Siddarth, et autres
Publié: (2024)

Towards SFW sampling for diffusion models via external conditioning
par: Reyes, Camilo Carvajal, et autres
Publié: (2025)

Boomerang: Local sampling on image manifolds using diffusion models
par: Luzi, Lorenzo, et autres
Publié: (2022)

Physics-informed diffusion models in spectral space
par: Gallon, Davide, et autres
Publié: (2026)

Bayesian computation with generative diffusion models by Multilevel Monte Carlo
par: Haji-Ali, Abdul-Lateef, et autres
Publié: (2024)

When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective
par: Zhou, Qiqi, et autres
Publié: (2024)

MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers
par: Li, Ao, et autres
Publié: (2025)

Generalization in diffusion models arises from geometry-adaptive harmonic representations
par: Kadkhodaie, Zahra, et autres
Publié: (2023)

Learning few-step posterior samplers by unfolding and distillation of diffusion models
par: Mbakam, Charlesquin Kemajou, et autres
Publié: (2025)

Critical windows: non-asymptotic theory for feature emergence in diffusion models
par: Li, Marvin, et autres
Publié: (2024)

Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
par: Hoogeboom, Emiel, et autres
Publié: (2024)

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
par: Bartosh, Grigory, et autres
Publié: (2026)

Inverse problems with diffusion models: MAP estimation via mode-seeking loss
par: Gutha, Sai Bharath Chandra, et autres
Publié: (2025)

Elucidating the Exposure Bias in Diffusion Models
par: Ning, Mang, et autres
Publié: (2023)

Elucidating the Design Space of Dataset Condensation
par: Shao, Shitong, et autres
Publié: (2024)

PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations
par: Dai, Ting-Yu, et autres
Publié: (2025)

A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context
par: Mateescu, Andrei, et autres
Publié: (2025)

Fine-tuning can cripple your foundation model; preserving features may be the solution
par: Mukhoti, Jishnu, et autres
Publié: (2023)

HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
par: Choi, Sungik, et autres
Publié: (2024)

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
par: Shang, Xinyi, et autres
Publié: (2024)

High-Resolution Image Reconstruction with Unsupervised Learning and Noisy Data Applied to Ion-Beam Dynamics for Particle Accelerators
par: Osswald, Francis, et autres
Publié: (2026)

Theoretical research on generative diffusion models: an overview
par: Yeğin, Melike Nur, et autres
Publié: (2024)

Information-geometric adaptive sampling for graph diffusion
par: Lu, Yuhui, et autres
Publié: (2026)

Guiding a diffusion model using sliding windows
par: Adaloglou, Nikolas, et autres
Publié: (2024)