Image de couverture de livre

Training-Free Vector Quantization via Gaussian VAEs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Tongda, Zheng, Wendi, He, Jiajun, Hernandez-Lobato, Jose Miguel, Wang, Yan, Zhang, Ya-Qin, Tang, Jie
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning 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

Making Reconstruction FID Predictive of Diffusion Generation FID
par: Xu, Tongda, et autres
Publié: (2026)

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization
par: Chang, Yifan, et autres
Publié: (2025)

PICD: Versatile Perceptual Image Compression with Diffusion Rendering
par: Xu, Tongda, et autres
Publié: (2025)

GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
par: Li, Tiantian, et autres
Publié: (2025)

V-Shuffle: Zero-Shot Style Transfer via Value Shuffle
par: Tang, Haojun, et autres
Publié: (2025)

Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
par: Xu, Tongda
Publié: (2025)

CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query
par: Wang, Zhe, et autres
Publié: (2025)

Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
par: Liu, Shizhan, et autres
Publié: (2025)

Training-Free Image Editing with Visual Context Integration and Concept Alignment
par: Song, Rui, et autres
Publié: (2026)

Training VAEs Under Structured Residuals
par: Dorta, Gara, et autres
Publié: (2018)

Preventing Local Pitfalls in Vector Quantization via Optimal Transport
par: Zhang, Borui, et autres
Publié: (2024)

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
par: Chen, Wenlin, et autres
Publié: (2025)

RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
par: Zheng, Chunhang, et autres
Publié: (2026)

Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
par: Xu, Hao, et autres
Publié: (2025)

Noise Dimension of GAN: An Image Compression Perspective
par: Zhu, Ziran, et autres
Publié: (2024)

CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
par: Navaneet, KL, et autres
Publié: (2023)

Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices
par: Zou, Ya, et autres
Publié: (2025)

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba
par: Deng, Juncan, et autres
Publié: (2025)

Autoregressive Image Generation without Vector Quantization
par: Li, Tianhong, et autres
Publié: (2024)

MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
par: Zhang, Xinjie, et autres
Publié: (2024)

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
par: Xu, Tongda, et autres
Publié: (2025)

Versatile Recompression-Aware Perceptual Image Super-Resolution
par: He, Mingwei, et autres
Publié: (2025)

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
par: Ding, Ning, et autres
Publié: (2025)

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
par: Zhang, Xinjie, et autres
Publié: (2024)

Fast Training-free Perceptual Image Compression
par: Zhu, Ziran, et autres
Publié: (2025)

SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing
par: Song, Xiaowei, et autres
Publié: (2024)

EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
par: Wang, Zhe, et autres
Publié: (2024)

FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation
par: Wang, Zhaorui, et autres
Publié: (2025)

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization
par: Li, Jie, et autres
Publié: (2026)

Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models
par: Zheng, Hong-Kai, et autres
Publié: (2025)

Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers
par: Xu, Tongda, et autres
Publié: (2024)

Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model
par: Sun, Jiajun, et autres
Publié: (2025)

Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
par: Wang, Haishan, et autres
Publié: (2025)

ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
par: Cao, Hao, et autres
Publié: (2026)

Quantize-then-Rectify: Efficient VQ-VAE Training
par: Zhang, Borui, et autres
Publié: (2025)

SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
par: Zhang, Haotian, et autres
Publié: (2026)

PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping
par: Wang, Tengfei, et autres
Publié: (2025)

Vector Quantized Feature Fields for Fast 3D Semantic Lifting
par: Tang, George, et autres
Publié: (2025)

Training-Free Large Model Priors for Multiple-in-One Image Restoration
par: He, Xuanhua, et autres
Publié: (2024)

SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
par: Li, Shuaiting, et autres
Publié: (2025)