Imagen de Portada

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Jiawei, Liu, Ziyuan, Yan, Leon, Li, Gen, Gu, Yuantao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Few-Step Diffusion via Score identity Distillation
por: Zhou, Mingyuan, et al.
Publicado: (2025)

M$^2$CD: A Unified MultiModal Framework for Optical-SAR Change Detection with Mixture of Experts and Self-Distillation
por: Liu, Ziyuan, et al.
Publicado: (2025)

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
por: Zhang, Ziyi, et al.
Publicado: (2025)

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
por: Tang, Jian, et al.
Publicado: (2026)

Improving Diffusion Models for Inverse Problems using Manifold Constraints
por: Chung, Hyungjin, et al.
Publicado: (2022)

Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
por: Bartosh, Grigory, et al.
Publicado: (2024)

ReDiF: Reinforced Distillation for Few Step Diffusion
por: Tighkhorshid, Amirhossein, et al.
Publicado: (2025)

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
por: Wu, Zhuguanyu, et al.
Publicado: (2026)

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
por: Zhang, Ziyi, et al.
Publicado: (2024)

Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
por: Zhang, Jiawei, et al.
Publicado: (2026)

Reflecting Topology Consistency and Abnormality via Learnable Attentions for Airway Labeling
por: Li, Chenyu, et al.
Publicado: (2024)

Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint
por: Qi, Zhi, et al.
Publicado: (2024)

Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts
por: Bui, Anh, et al.
Publicado: (2024)

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
por: Chadebec, Clément, et al.
Publicado: (2024)

FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
por: Liu, Dong, et al.
Publicado: (2025)

TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers
por: Liu, Yihua, et al.
Publicado: (2026)

Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
por: Peng, Xinyu, et al.
Publicado: (2024)

One Step Diffusion via Shortcut Models
por: Frans, Kevin, et al.
Publicado: (2024)

MedCRP-CL: Continual Medical Image Segmentation via Bayesian Nonparametric Semantic Modality Discovery
por: Gao, Ziyuan
Publicado: (2026)

Optimizing Few-Step Generation with Adaptive Matching Distillation
por: Bai, Lichen, et al.
Publicado: (2026)

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
por: Xue, Haotian, et al.
Publicado: (2025)

Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
por: Sfountouris, Loukas, et al.
Publicado: (2025)

SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems
por: Alkhouri, Ismail, et al.
Publicado: (2024)

Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint
por: Li, Yukun, et al.
Publicado: (2024)

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
por: Zhang, Yasi, et al.
Publicado: (2024)

On the Learnability of Out-of-distribution Detection
por: Fang, Zhen, et al.
Publicado: (2024)

One-Step Diffusion Distillation via Deep Equilibrium Models
por: Geng, Zhengyang, et al.
Publicado: (2023)

Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems
por: Meng, Xiangming, et al.
Publicado: (2022)

Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Tasks
por: Oh, Changgyoon, et al.
Publicado: (2025)

Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention
por: Gu, Jiawei, et al.
Publicado: (2025)

SLA2: Sparse-Linear Attention with Learnable Routing and QAT
por: Zhang, Jintao, et al.
Publicado: (2026)

It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Steps
por: Cisneros-Velarde, Pedro
Publicado: (2025)

Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
por: Zhang, Bingliang, et al.
Publicado: (2024)

Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers
por: Xu, Tongda, et al.
Publicado: (2024)

Training-free Linear Image Inverses via Flows
por: Pokle, Ashwini, et al.
Publicado: (2023)

VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning
por: Yan, Jiawei
Publicado: (2026)

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
por: Chen, Hansheng, et al.
Publicado: (2025)

JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework
por: Liu, Ziyuan, et al.
Publicado: (2025)

AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation
por: Gao, Ziyuan
Publicado: (2025)

Stability Plasticity Decoupled Fine-tuning For Few-shot end-to-end Object Detection
por: Yin, Yuantao, et al.
Publicado: (2024)