Image de couverture de livre

Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ren, Qin, Wang, Yufei, Guo, Lanqing, Zhang, Wen, Fan, Zhiwen, You, Chenyu
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

Training-Free Text-Guided Image Editing with Visual Autoregressive Model
par: Wang, Yufei, et autres
Publié: (2025)

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
par: Guo, Lanqing, et autres
Publié: (2024)

Supervise Less, See More: Training-free Nuclear Instance Segmentation with Prototype-Guided Prompting
par: Zhang, Wen, et autres
Publié: (2025)

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
par: Qiu, Haonan, et autres
Publié: (2024)

Making Training-Free Diffusion Segmentors Scale with the Generative Power
par: Meng, Benyuan, et autres
Publié: (2026)

Together, Then Apart: Revisiting Multimodal Survival Analysis via a Min-Max Perspective
par: Liu, Wenjing, et autres
Publié: (2025)

Calibrating Where It Matters: Constrained Temperature Scaling
par: McKenna, Stephen, et autres
Publié: (2024)

Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
par: Fu, Zixuan, et autres
Publié: (2024)

Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
par: Sun, Shanlin, et autres
Publié: (2025)

Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization
par: Li, Guandong, et autres
Publié: (2026)

Controlling Your Image via Simplified Vector Graphics
par: Guo, Lanqing, et autres
Publié: (2026)

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
par: Zhu, Libo, et autres
Publié: (2024)

HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models
par: He, Yeqi, et autres
Publié: (2026)

InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
par: Liang, Jiabin, et autres
Publié: (2024)

ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model
par: Wang, Yufei, et autres
Publié: (2024)

Satellite-Free Training for Drone-View Geo-Localization
par: Liu, Tao, et autres
Publié: (2026)

FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection
par: Zhang, Ruiqiang, et autres
Publié: (2026)

Let EEG Models Learn EEG
par: Wang, Yifan, et autres
Publié: (2026)

OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transport
par: Ren, Qin, et autres
Publié: (2025)

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
par: Wei, Yujie, et autres
Publié: (2025)

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models
par: Fei, Zhengcong, et autres
Publié: (2024)

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual
par: Wang, Chong, et autres
Publié: (2025)

Can Test-Time Scaling Improve World Foundation Model?
par: Cong, Wenyan, et autres
Publié: (2025)

SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
par: Yan, Zhengan, et autres
Publié: (2026)

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
par: Hu, Hezhen, et autres
Publié: (2026)

Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search
par: Zhou, Yunqi, et autres
Publié: (2025)

Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks
par: Wang, Chong, et autres
Publié: (2024)

OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution
par: Chai, Xinning, et autres
Publié: (2025)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
par: Liu, Yexin, et autres
Publié: (2025)

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
par: Qian, Zhaofang, et autres
Publié: (2025)

D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal
par: Li, Linhao, et autres
Publié: (2025)

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
par: Wang, Chong, et autres
Publié: (2024)

Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
par: Li, Wenhao, et autres
Publié: (2023)

NanoGS: Training-Free Gaussian Splat Simplification
par: Xiong, Butian, et autres
Publié: (2026)

OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner
par: Jiang, Haoyang, et autres
Publié: (2026)

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
par: Ma, Nanye, et autres
Publié: (2025)

A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model
par: Park, Jihun, et autres
Publié: (2025)

Scaling Dense Event-Stream Pretraining from Visual Foundation Models
par: Chen, Zhiwen, et autres
Publié: (2026)

SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal
par: Wang, Xinrui, et autres
Publié: (2024)

JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on
par: Wang, Aowen, et autres
Publié: (2025)