Imagen de Portada

Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Saito, Shinnosuke, Matsubara, Takashi
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

Image Interpolation with Score-based Riemannian Metrics of Diffusion Models
por: Saito, Shinnosuke, et al.
Publicado: (2025)

Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
por: Sueyoshi, Kota, et al.
Publicado: (2023)

What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
por: Azeglio, Simone, et al.
Publicado: (2025)

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

NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
por: Takezaki, Shumpei, et al.
Publicado: (2025)

TCFG: Tangential Damping Classifier-free Guidance
por: Kwon, Mingi, et al.
Publicado: (2025)

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
por: Cho, Hyunmin, et al.
Publicado: (2025)

PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
por: Yoshikawa, Daiki, et al.
Publicado: (2025)

Bring Metric Functions into Diffusion Models
por: An, Jie, et al.
Publicado: (2024)

Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry
por: Álvarez-Tuñón, Olaya, et al.
Publicado: (2023)

Unbiased Image Synthesis via Manifold Guidance in Diffusion Models
por: Su, Xingzhe, et al.
Publicado: (2023)

ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection
por: Hong, Chengzhi, et al.
Publicado: (2026)

DEGMC: Denoising Diffusion Models Based on Riemannian Equivariant Group Morphological Convolutions
por: Diop, El Hadji S., et al.
Publicado: (2026)

GP-PCS: One-shot Feature-Preserving Point Cloud Simplification with Gaussian Processes on Riemannian Manifolds
por: Pathak, Stuti, et al.
Publicado: (2023)

RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization
por: Li, Yan, et al.
Publicado: (2025)

Adversarial Examples are Misaligned in Diffusion Model Manifolds
por: Lorenz, Peter, et al.
Publicado: (2024)

Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models
por: Haas, René, et al.
Publicado: (2023)

Attention Lattice Adapter: Visual Explanation Generation for Visual Foundation Model
por: Hirano, Shinnosuke, et al.
Publicado: (2025)

Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models
por: Xu, Katherine, et al.
Publicado: (2024)

FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions
por: Jiang, Yilei, et al.
Publicado: (2024)

Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samples
por: Saito, Reiji, et al.
Publicado: (2026)

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
por: Li, Hang, et al.
Publicado: (2023)

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
por: Yue, Zhengrong, et al.
Publicado: (2026)

RemEdit: Efficient Diffusion Editing with Riemannian Geometry
por: Adhikarla, Eashan, et al.
Publicado: (2026)

Computer-Aided Multi-Stroke Character Simplification by Stroke Removal
por: Ishiyama, Ryo, et al.
Publicado: (2025)

High-Dimensional Noise to Low-Dimensional Manifolds: A Manifold-Space Diffusion Framework for Degraded Hyperspectral Image Classification
por: Yang, Boxiang, et al.
Publicado: (2026)

Flows and Diffusions on the Neural Manifold
por: Saragih, Daniel, et al.
Publicado: (2025)

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
por: Kim, Hyeonwoo, et al.
Publicado: (2024)

Manifold Sampling for Differentiable Uncertainty in Radiance Fields
por: Lyu, Linjie, et al.
Publicado: (2024)

HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery
por: Matsubara, Yuto, et al.
Publicado: (2024)

Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
por: Xue, Duoduo, et al.
Publicado: (2026)

Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models
por: Miyake, Daiki, et al.
Publicado: (2023)

Uniform Discrete Diffusion with Metric Path for Video Generation
por: Deng, Haoge, et al.
Publicado: (2025)

VoxelDiffusionCut: Non-destructive Internal-part Extraction via Iterative Cutting and Structure Estimation
por: Hachimine, Takumi, et al.
Publicado: (2026)

Discovering Divergent Representations between Text-to-Image Models
por: Dunlap, Lisa, et al.
Publicado: (2025)

Leveraging Vision-Language Models as Weak Annotators in Active Learning
por: Nguyen, Phuong Ngoc, et al.
Publicado: (2026)

GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
por: Pham, Tuan, et al.
Publicado: (2025)

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
por: Roy, Ayush, et al.
Publicado: (2026)

DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration
por: Gao, Nan, et al.
Publicado: (2024)

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
por: Kaito, Shiku, et al.
Publicado: (2025)