Image de couverture de livre

Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jia, Zexi, Luo, Pengcheng, Fang, Zhengyao, Zhang, Jinchao, Zhou, Jie
Format:	Preprint
Publié:	2026
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

Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation
par: Jia, Zexi, et autres
Publié: (2025)

Evaluating Generative Models via One-Dimensional Code Distributions
par: Jia, Zexi, et autres
Publié: (2026)

Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity
par: Fang, Zhengyao, et autres
Publié: (2026)

StyleDecoupler: Generalizable Artistic Style Disentanglement
par: Jia, Zexi, et autres
Publié: (2026)

Unbiased Image Synthesis via Manifold Guidance in Diffusion Models
par: Su, Xingzhe, et autres
Publié: (2023)

Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection
par: Fei, Hongyan, et autres
Publié: (2026)

Readout Guidance: Learning Control from Diffusion Features
par: Luo, Grace, et autres
Publié: (2023)

Unified Control for Inference-Time Guidance of Denoising Diffusion Models
par: Goyal, Maurya, et autres
Publié: (2025)

Structural Energy Guidance for View-Consistent Text-to-3D Generation
par: Zhang, Qing, et autres
Publié: (2026)

CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection
par: Jia, Zexi, et autres
Publié: (2026)

Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance
par: Arrabi, Ahmad, et autres
Publié: (2024)

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
par: Chen, Dar-Yen, et autres
Publié: (2025)

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
par: Roy, Ayush, et autres
Publié: (2026)

Semantic to Structure: Learning Structural Representations for Infringement Detection
par: Huang, Chuanwei, et autres
Publié: (2025)

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation
par: Yuan, Zhiqiang, et autres
Publié: (2025)

Feedback Guidance of Diffusion Models
par: Koulischer, Felix, et autres
Publié: (2025)

TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
par: Zeng, Weichao, et autres
Publié: (2024)

Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance
par: Wang, Jiacheng, et autres
Publié: (2024)

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

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
par: Jang, Sangwon, et autres
Publié: (2025)

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
par: Chung, Hyungjin, et autres
Publié: (2024)

Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
par: Xue, Naifu, et autres
Publié: (2025)

IntelliCap: Intelligent Guidance for Consistent View Sampling
par: Yasunaga, Ayaka, et autres
Publié: (2025)

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets
par: Jia, Zexi, et autres
Publié: (2025)

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

Dynamic Negative Guidance of Diffusion Models
par: Koulischer, Felix, et autres
Publié: (2024)

OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
par: Wang, Cong, et autres
Publié: (2026)

Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
par: Jiang, Zhou, et autres
Publié: (2026)

MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
par: Xie, Jianhao, et autres
Publié: (2025)

Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance
par: Li, Lisha, et autres
Publié: (2025)

InstructX: Towards Unified Visual Editing with MLLM Guidance
par: Mou, Chong, et autres
Publié: (2025)

Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models
par: Yin, Yuanyang, et autres
Publié: (2026)

One-Shot Crowd Counting With Density Guidance For Scene Adaptation
par: Chen, Jiwei, et autres
Publié: (2026)

EventRPG: Event Data Augmentation with Relevance Propagation Guidance
par: Sun, Mingyuan, et autres
Publié: (2024)

Variational Control for Guidance in Diffusion Models
par: Pandey, Kushagra, et autres
Publié: (2025)

Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models
par: Saito, Shinnosuke, et autres
Publié: (2025)

Unpaired Multi-view Clustering via Reliable View Guidance
par: Xin, Like, et autres
Publié: (2024)

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
par: Yuan, Liangyu, et autres
Publié: (2026)

DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance
par: Zhang, Peiying, et autres
Publié: (2025)

DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation
par: Yan, Junkai, et autres
Publié: (2024)