Image de couverture de livre

EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yadav, Ankit, Huy, Ta Duc, Liu, Lingqiao
Format:	Preprint
Publié:	2025
Sujets:	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

STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
par: Yadav, Ankit, et autres
Publié: (2026)

Revisiting Vision Language Foundations for No-Reference Image Quality Assessment
par: Yadav, Ankit, et autres
Publié: (2025)

Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models
par: Yadav, Ankit, et autres
Publié: (2025)

RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling
par: Sanjyal, Ankit
Publié: (2025)

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
par: Ahn, Donghoon, et autres
Publié: (2024)

Rectified Diffusion Guidance for Conditional Generation
par: Xia, Mengfei, et autres
Publié: (2024)

Boosting Diffusion Models with Moving Average Sampling in Frequency Domain
par: Qian, Yurui, et autres
Publié: (2024)

Entropy Rectifying Guidance for Diffusion and Flow Models
par: Ifriqi, Tariq Berrada, et autres
Publié: (2025)

Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images
par: Xia, Jiatong, et autres
Publié: (2026)

Break a Lag: Triple Exponential Moving Average for Enhanced Optimization
par: Peleg, Roi, et autres
Publié: (2023)

EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos
par: Hatano, Masashi, et autres
Publié: (2024)

Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance
par: Che, Quang-Huy, et autres
Publié: (2024)

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
par: Wang, Fu-Yun, et autres
Publié: (2024)

Close-up-GS: Enhancing Close-Up View Synthesis in 3D Gaussian Splatting with Progressive Self-Training
par: Xia, Jiatong, et autres
Publié: (2025)

REG: Rectified Gradient Guidance for Conditional Diffusion Models
par: Gao, Zhengqi, et autres
Publié: (2025)

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
par: Nguyen, Thong, et autres
Publié: (2023)

Compress Guidance in Conditional Diffusion Sampling
par: Dinh, Anh-Dung, et autres
Publié: (2024)

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
par: Hyung, Junha, et autres
Publié: (2024)

Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
par: Li, Tiancheng, et autres
Publié: (2024)

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
par: Zhu, Yuanzhi, et autres
Publié: (2024)

Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
par: Kim, Wonjune, et autres
Publié: (2025)

Categorical Keypoint Positional Embedding for Robust Animal Re-Identification
par: Lin, Yuhao, et autres
Publié: (2024)

GS-EMA: Integrating Gradient Surgery Exponential Moving Average with Boundary-Aware Contrastive Learning for Enhanced Domain Generalization in Aneurysm Segmentation
par: Lin, Fengming, et autres
Publié: (2024)

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
par: Sun, Zhicheng, et autres
Publié: (2024)

A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler
par: Yadav, Ankit, et autres
Publié: (2024)

Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review
par: Yadav, Ankit, et autres
Publié: (2024)

Towards Effective Image Forensics via A Novel Computationally Efficient Framework and A New Image Splice Dataset
par: Yadav, Ankit, et autres
Publié: (2024)

CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation
par: Wang, Haoxuan, et autres
Publié: (2025)

Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
par: Chen, Chubin, et autres
Publié: (2025)

TriLiteNet: Lightweight Model for Multi-Task Visual Perception
par: Che, Quang-Huy, et autres
Publié: (2025)

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
par: Sun, Lingchen, et autres
Publié: (2026)

A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
par: Xiao, Ling, et autres
Publié: (2026)

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
par: Chu, Ruihang, et autres
Publié: (2025)

EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation
par: Dialameh, Maryam, et autres
Publié: (2025)

On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition
par: Wang, Zihu, et autres
Publié: (2024)

Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
par: Petersen, Richard, et autres
Publié: (2026)

Diffusion Mental Averages
par: Thawatdamrongkit, Phonphrm, et autres
Publié: (2026)

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects
par: Qiu, Weimin, et autres
Publié: (2024)

Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
par: Ma, Lina, et autres
Publié: (2025)

Move Anything with Layered Scene Diffusion
par: Ren, Jiawei, et autres
Publié: (2024)