Imagen de Portada

SPG: Improving Motion Diffusion by Smooth Perturbation Guidance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Jeon, Boseong
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ControlFill: Spatially Adjustable Image Inpainting from Prompt Learning
por: Jeon, Boseong
Publicado: (2025)

SPG: Style-Prompting Guidance for Style-Specific Content Creation
por: Liang, Qian, et al.
Publicado: (2025)

DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning
por: Lu, Jialang, et al.
Publicado: (2025)

Leveraging Topological Guidance for Improved Knowledge Distillation
por: Jeon, Eun Som, et al.
Publicado: (2024)

Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators
por: Geng, Daniel, et al.
Publicado: (2024)

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
por: Yuan, Liangyu, et al.
Publicado: (2026)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
por: Hu, Hanjiang, et al.
Publicado: (2023)

Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
por: Choi, June Suk, et al.
Publicado: (2025)

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
por: Ahn, Donghoon, et al.
Publicado: (2025)

Guidance-base Diffusion Models for Improving Photoacoustic Image Quality
por: Eguchi, Tatsuhiro, et al.
Publicado: (2025)

SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detection
por: Nanaumi, Tomoyasu, et al.
Publicado: (2026)

From Diffusion to Flow: Efficient Motion Generation in MotionGPT3
por: Ban, Jaymin, et al.
Publicado: (2026)

STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
por: Yadav, Ankit, et al.
Publicado: (2026)

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
por: Ahn, Donghoon, et al.
Publicado: (2024)

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance
por: Wang, Haoxuan, et al.
Publicado: (2025)

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
por: Jeon, Wooseok, et al.
Publicado: (2026)

FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
por: Wang, Zhen, et al.
Publicado: (2026)

Gradient-Free Classifier Guidance for Diffusion Model Sampling
por: Shenoy, Rahul, et al.
Publicado: (2024)

MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance
por: Yesiltepe, Hidir, et al.
Publicado: (2024)

Motion Blur Decomposition with Cross-shutter Guidance
por: Ji, Xiang, et al.
Publicado: (2024)

CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement
por: Jeon, Boseong, et al.
Publicado: (2025)

Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
por: Jeon, Wooseok, et al.
Publicado: (2026)

Human Motion Prediction under Unexpected Perturbation
por: Yue, Jiangbei, et al.
Publicado: (2024)

Less is More: Improving Motion Diffusion Models with Sparse Keyframes
por: Bae, Jinseok, et al.
Publicado: (2025)

DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations
por: Fathi, Nima, et al.
Publicado: (2024)

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
por: Chen, Dar-Yen, et al.
Publicado: (2025)

Feedback Guidance of Diffusion Models
por: Koulischer, Felix, et al.
Publicado: (2025)

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
por: Shi, Qingyu, et al.
Publicado: (2025)

Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
por: Choi, Soojin, et al.
Publicado: (2026)

Understanding and Improving Training-free Loss-based Diffusion Guidance
por: Shen, Yifei, et al.
Publicado: (2024)

From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models
por: Barquero, German, et al.
Publicado: (2025)

Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidance
por: Li, Zhengxuan, et al.
Publicado: (2025)

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

Rectified Diffusion Guidance for Conditional Generation
por: Xia, Mengfei, et al.
Publicado: (2024)

Dynamic Negative Guidance of Diffusion Models
por: Koulischer, Felix, et al.
Publicado: (2024)

Point-to-Point: Sparse Motion Guidance for Controllable Video Editing
por: Song, Yeji, et al.
Publicado: (2025)

Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance
por: Ji, Xiang, et al.
Publicado: (2026)

ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis
por: Heo, KunHo, et al.
Publicado: (2026)

Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance
por: Jia, Zexi, et al.
Publicado: (2026)

Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
por: Hong, Susung
Publicado: (2024)