Copertina

Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ning, Mang, Li, Mingxiao, Zhang, Le, Liu, Lanmiao, Blaschko, Matthew B., Salah, Albert Ali, Ertugrul, Itir Onal
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Elucidating the Exposure Bias in Diffusion Models
di: Ning, Mang, et al.
Pubblicazione: (2023)

Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
di: Ning, Mang, et al.
Pubblicazione: (2024)

DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
di: Ning, Mang, et al.
Pubblicazione: (2024)

RiT: Vanilla Diffusion Transformers Suffice in Representation Space
di: Zhang, Le, et al.
Pubblicazione: (2026)

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
di: Li, Mingxiao, et al.
Pubblicazione: (2025)

Context Matters: Vision-Based Depression Detection Comparing Classical and Deep Approaches
di: Bilalpur, Maneesh, et al.
Pubblicazione: (2026)

HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching
di: Liu, Lanmiao, et al.
Pubblicazione: (2026)

Boosting Latent Diffusion with Flow Matching
di: Schusterbauer, Johannes, et al.
Pubblicazione: (2023)

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
di: Liu, Enshu, et al.
Pubblicazione: (2024)

Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
di: Liu, Shizhan, et al.
Pubblicazione: (2025)

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
di: Wang, Zifu, et al.
Pubblicazione: (2023)

From Visual Explanations to Counterfactual Explanations with Latent Diffusion
di: Luu, Tung, et al.
Pubblicazione: (2025)

NAB: Neural Adaptive Binning for Sparse-View CT reconstruction
di: Xie, Wangduo, et al.
Pubblicazione: (2026)

MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs
di: Li, Jiameng, et al.
Pubblicazione: (2026)

SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
di: Xu, Dongli, et al.
Pubblicazione: (2025)

SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning
di: Liu, Lanmiao, et al.
Pubblicazione: (2025)

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
di: Jia, Haozhe, et al.
Pubblicazione: (2025)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
di: Li, Quanhao, et al.
Pubblicazione: (2026)

Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
di: Zhu, Kaizhen, et al.
Pubblicazione: (2025)

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
di: Yang, Haoxin, et al.
Pubblicazione: (2025)

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

Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
di: Lai, Bolin, et al.
Pubblicazione: (2025)

UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
di: Zhang, Jiacheng, et al.
Pubblicazione: (2024)

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
di: Li, Mingxiao, et al.
Pubblicazione: (2023)

IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
di: Zhai, Yuanhao, et al.
Pubblicazione: (2024)

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
di: Mao, Qi, et al.
Pubblicazione: (2025)

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
di: Jiang, Hai, et al.
Pubblicazione: (2024)

FSP-Diff: Full-Spectrum Prior-Enhanced DualDomain Latent Diffusion for Ultra-Low-Dose Spectral CT Reconstruction
di: Peng, Peng, et al.
Pubblicazione: (2026)

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
di: Zeng, Yu, et al.
Pubblicazione: (2024)

Snakes and Ladders: Two Steps Up for VideoMamba
di: Lu, Hui, et al.
Pubblicazione: (2024)

TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions
di: Lu, Hui, et al.
Pubblicazione: (2024)

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
di: Zhou, Yifan, et al.
Pubblicazione: (2025)

Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss
di: Zhou, Han, et al.
Pubblicazione: (2025)

Diffusion Model for Dense Matching
di: Nam, Jisu, et al.
Pubblicazione: (2023)

DuoGesture: Neuro-Inspired and Biomechanically Informed Dual-Stream Co-Speech Gesture Generation
di: Paar, Ferdinand, et al.
Pubblicazione: (2026)

Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion
di: Tang, Yingzhi, et al.
Pubblicazione: (2026)

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
di: Zhang, Jinjin, et al.
Pubblicazione: (2025)

LatentCRF: Continuous CRF for Efficient Latent Diffusion
di: Ranasinghe, Kanchana, et al.
Pubblicazione: (2024)

Diffuse to Choose: Enriching Image Conditioned Inpainting in Latent Diffusion Models for Virtual Try-All
di: Seyfioglu, Mehmet Saygin, et al.
Pubblicazione: (2024)

Latte: Latent Diffusion Transformer for Video Generation
di: Ma, Xin, et al.
Pubblicazione: (2024)