English
Related papers

Related papers: RestoreVAR: Visual Autoregressive Generation for A…

200 papers

Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve the curve-like…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Haoxi Ran , Vitor Guizilini , Yue Wang

Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Bulat Gabdullin , Nina Konovalova , Nikolay Patakin , Dmitry Senushkin , Anton Konushin

Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Hang Guo , Tao Dai , Zhihao Ouyang , Taolin Zhang , Yaohua Zha , Bin Chen , Shu-tao Xia

Autoregressive (AR) image generators offer a language-model-friendly approach to image generation by predicting discrete image tokens in a causal sequence. However, unlike diffusion models, AR models lack a mechanism to refine previous…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Cheng Cheng , Lin Song , Di An , Yicheng Xiao , Xuchong Zhang , Hongbin Sun , Ying Shan

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

Image and Video Processing · Electrical Eng. & Systems 2024-05-24 Marc Windsheimer , Fabian Brand , André Kaup

Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…

Sound · Computer Science 2025-02-11 Tushar Dhyani , Florian Lux , Michele Mancusi , Giorgio Fabbro , Fritz Hohl , Ngoc Thang Vu

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Qihang Yu , Ju He , Xueqing Deng , Xiaohui Shen , Liang-Chieh Chen

Diffusion models have been widely utilized for image restoration. However, previous blind image restoration methods still need to assume the type of degradation model while leaving the parameters to be optimized, limiting their real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Siwei Tu , Weidong Yang , Ben Fei

AI-generated content (AIGC) enables efficient visual creation but raises copyright and authenticity risks. As a common technique for integrity verification and source tracing, digital image watermarking is regarded as a potential solution…

Multimedia · Computer Science 2025-12-23 Yuzhuo Chen , Zehua Ma , Han Fang , Weiming Zhang , Nenghai Yu

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencoders like VQGAN or…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Yongxin Zhu , Bocheng Li , Hang Zhang , Xin Li , Linli Xu , Lidong Bing

Recent advancements in image restoration increasingly employ conditional latent diffusion models (CLDMs). While these models have demonstrated notable performance improvements in recent years, this work questions their suitability for IR…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Yunchen Yuan , Junyuan Xiao , Xinjie Li

The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomenon. Latent diffusion models (LDMs), which operate on the…

Machine Learning · Computer Science 2026-03-26 Mingxing Rao , Bowen Qu , Daniel Moyer

This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Liang Chen , Sinan Tan , Zefan Cai , Weichu Xie , Haozhe Zhao , Yichi Zhang , Junyang Lin , Jinze Bai , Tianyu Liu , Baobao Chang

Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Gengze Zhou , Chongjian Ge , Hao Tan , Feng Liu , Yicong Hong

Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images. However, the naive application of DMs presents several key limitations. (i) The…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Senmao Li , Kai Wang , Joost van de Weijer , Fahad Shahbaz Khan , Chun-Le Guo , Shiqi Yang , Yaxing Wang , Jian Yang , Ming-Ming Cheng

Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Zekun Li , Ning Wang , Tongxin Bai , Changwang Mei , Peisong Wang , Shuang Qiu , Jian Cheng

Text-to-image generation with visual autoregressive~(VAR) models has recently achieved impressive advances in generation fidelity and inference efficiency. While control mechanisms have been explored for diffusion models, enabling precise…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Keli Liu , Zhendong Wang , Wengang Zhou , Shaodong Xu , Ruixiao Dong , Houqiang Li

Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Zhekai Chen , Ruihang Chu , Yukang Chen , Shiwei Zhang , Yujie Wei , Yingya Zhang , Xihui Liu

Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiarui Guan , Wenshuai Zhao , Zhengtao Zou , Juho Kannala , Arno Solin

Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short video sequences and suffer from significant performance…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Haotian Zhang , Xu Mo , Yixin Yu , Guanhua Zhu , Jian Xue , Tongda Xu , Yan Wang , Jiaqi Zhang , Siwei Ma , Wen Gao