Imagen de Portada

A Tilted Seesaw: Revisiting Autoencoder Trade-off for Controllable Diffusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Pu, Ma, Yiyang, Zhou, Feng, Yin, Xuedan, Song, Qing, Yang, Lu
Formato:	Preprint
Publicado:	2026
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

ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformers
por: Ma, Yiyang, et al.
Publicado: (2025)

Controllable Generation with Text-to-Image Diffusion Models: A Survey
por: Cao, Pu, et al.
Publicado: (2024)

Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation
por: Zhou, Feng, et al.
Publicado: (2025)

Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation
por: Cao, Pu, et al.
Publicado: (2023)

S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression
por: Chen, Yunuo, et al.
Publicado: (2025)

Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution
por: Wang, Dan, et al.
Publicado: (2026)

Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters
por: Wei, Xingxing, et al.
Publicado: (2023)

Fourier Series Coder: A Novel Perspective on Angle Boundary Discontinuity Problem for Oriented Object Detection
por: Wei, Minghong, et al.
Publicado: (2026)

Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality
por: Khungurn, Pramook, et al.
Publicado: (2025)

Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS
por: Zhou, Feng, et al.
Publicado: (2025)

OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation
por: Wang, Lizhi, et al.
Publicado: (2024)

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
por: Chen, Chen, et al.
Publicado: (2025)

E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance
por: Huang, Tianrui, et al.
Publicado: (2024)

Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
por: Shen, Yiyang, et al.
Publicado: (2026)

MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
por: Yang, Han, et al.
Publicado: (2024)

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
por: Tong, Shengbang, et al.
Publicado: (2026)

Trade-offs in Image Generation: How Do Different Dimensions Interact?
por: Zhang, Sicheng, et al.
Publicado: (2025)

Frequency-based Matcher for Long-tailed Semantic Segmentation
por: Li, Shan, et al.
Publicado: (2024)

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
por: Lu, Aojun, et al.
Publicado: (2025)

Revisiting Diffusion Model Predictions Through Dimensionality
por: Jin, Qing, et al.
Publicado: (2026)

Diffusion Transformers with Representation Autoencoders
por: Zheng, Boyang, et al.
Publicado: (2025)

Adaptive 1D Video Diffusion Autoencoder
por: Teng, Yao, et al.
Publicado: (2026)

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
por: Chen, Junyu, et al.
Publicado: (2024)

Geometric Autoencoder for Diffusion Models
por: Liu, Hangyu, et al.
Publicado: (2026)

IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off
por: Dai, Linyan, et al.
Publicado: (2026)

At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections
por: Ho, Ming-Yang, et al.
Publicado: (2026)

PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
por: Guo, Jinhui, et al.
Publicado: (2025)

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
por: Cao, Ke, et al.
Publicado: (2025)

Controllable 3D Face Generation with Conditional Style Code Diffusion
por: Shen, Xiaolong, et al.
Publicado: (2023)

Latent Diffusion Model without Variational Autoencoder
por: Shi, Minglei, et al.
Publicado: (2025)

High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
por: Shen, Yiyang, et al.
Publicado: (2025)

StegOT: Trade-offs in Steganography via Optimal Transport
por: Lin, Chengde, et al.
Publicado: (2025)

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
por: Zhang, Jiacheng, et al.
Publicado: (2024)

Laminating Representation Autoencoders for Efficient Diffusion
por: Calvo-González, Ramón, et al.
Publicado: (2026)

DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment
por: Bounareli, Stella, et al.
Publicado: (2024)

DisControlFace: Adding Disentangled Control to Diffusion Autoencoder for One-shot Explicit Facial Image Editing
por: Jia, Haozhe, et al.
Publicado: (2023)

Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models
por: Yin, Yuanyang, et al.
Publicado: (2026)

Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
por: Lee, Cheng-Yi, et al.
Publicado: (2024)

LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space
por: Zhao, Xuekun, et al.
Publicado: (2022)

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
por: Shi, Minglei, et al.
Publicado: (2025)