Image de couverture de livre

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Lingchen, Wu, Rongyuan, Zhang, Zhengqiang, Li, Ruibin, Sun, Yujing, Liu, Shuaizheng, Zhang, Lei
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

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
par: Sun, Yujing, et autres
Publié: (2025)

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
par: Zhang, Zhengqiang, et autres
Publié: (2025)

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
par: Kong, Xiangtao, et autres
Publié: (2025)

Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
par: Sun, Lingchen, et autres
Publié: (2024)

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
par: Wu, Rongyuan, et autres
Publié: (2023)

GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
par: Yi, Qiaosi, et autres
Publié: (2026)

Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
par: Sun, Lingchen, et autres
Publié: (2023)

NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
par: Liang, Jie, et autres
Publié: (2025)

VOSR: A Vision-Only Generative Model for Image Super-Resolution
par: Wu, Rongyuan, et autres
Publié: (2026)

One-Step Effective Diffusion Network for Real-World Image Super-Resolution
par: Wu, Rongyuan, et autres
Publié: (2024)

Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
par: Yi, Qiaosi, et autres
Publié: (2025)

InstructRestore: Region-Customized Image Restoration with Human Instructions
par: Liu, Shuaizheng, et autres
Publié: (2025)

DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
par: Wu, Rongyuan, et autres
Publié: (2025)

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration
par: Kong, Xiangtao, et autres
Publié: (2026)

NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge
par: Liang, Jie, et autres
Publié: (2024)

Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective
par: Sun, Lingchen, et autres
Publié: (2023)

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers
par: Xiao, Chaodong, et autres
Publié: (2026)

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers
par: Sun, Wenhao, et autres
Publié: (2026)

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
par: Huang, Yushi, et autres
Publié: (2024)

Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models
par: Wei, Hongyang, et autres
Publié: (2025)

Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization
par: Yang, Tao, et autres
Publié: (2023)

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
par: Zhang, Zhengqiang, et autres
Publié: (2024)

SSL: A Self-similarity Loss for Improving Generative Image Super-resolution
par: Chen, Du, et autres
Publié: (2024)

Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
par: Chen, Chubin, et autres
Publié: (2025)

Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models
par: Li, Ruibin, et autres
Publié: (2024)

RORem: Training a Robust Object Remover with Human-in-the-Loop
par: Li, Ruibin, et autres
Publié: (2025)

BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
par: Zhang, Hui, et autres
Publié: (2025)

Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidance
par: Sun, Guodong, et autres
Publié: (2026)

Adversarial Diffusion Compression for Real-World Image Super-Resolution
par: Chen, Bin, et autres
Publié: (2024)

Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement
par: Liang, Xinyue, et autres
Publié: (2025)

AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
par: Liang, Xinyue, et autres
Publié: (2025)

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data
par: Ma, Zhiyuan, et autres
Publié: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
par: Zou, Chang, et autres
Publié: (2026)

No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
par: Jiang, Dengyang, et autres
Publié: (2025)

OUSAC: Optimized Guidance Scheduling with Adaptive Caching for DiT Acceleration
par: Sun, Ruitong, et autres
Publié: (2025)

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
par: Wu, Tianhe, et autres
Publié: (2026)

CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion
par: Li, Yanyu, et autres
Publié: (2025)

Extreme Two-View Geometry From Object Poses with Diffusion Models
par: Sun, Yujing, et autres
Publié: (2024)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
par: Liu, Jiacheng, et autres
Publié: (2025)