中文
相关论文

相关论文: Layton: Latent Consistency Tokenizer for 1024-pixe…

200 篇论文

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song…

计算机视觉与模式识别 · 计算机科学 2023-10-09 Simian Luo , Yiqin Tan , Longbo Huang , Jian Li , Hang Zhao

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational…

计算机视觉与模式识别 · 计算机科学 2024-06-12 Qihang Yu , Mark Weber , Xueqing Deng , Xiaohui Shen , Daniel Cremers , Liang-Chieh Chen

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new…

计算机视觉与模式识别 · 计算机科学 2021-12-21 Yanhong Zeng , Huan Yang , Hongyang Chao , Jianbo Wang , Jianlong Fu

Generative 3D Painting is among the top productivity boosters in high-resolution 3D asset management and recycling. Ever since text-to-image models became accessible for inference on consumer hardware, the performance of 3D Painting methods…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Tianfu Wang , Anton Obukhov , Konrad Schindler

Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models. However, the consistency model in the…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Xiang Wang , Shiwei Zhang , Han Zhang , Yu Liu , Yingya Zhang , Changxin Gao , Nong Sang

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Andreas Blattmann , Robin Rombach , Huan Ling , Tim Dockhorn , Seung Wook Kim , Sanja Fidler , Karsten Kreis

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Shilong Zhang , He Zhang , Zhifei Zhang , Chongjian Ge , Shuchen Xue , Shaoteng Liu , Mengwei Ren , Soo Ye Kim , Yuqian Zhou , Qing Liu , Daniil Pakhomov , Kai Zhang , Zhe Lin , Ping Luo

The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Yan Li , Ning Liao , Xiangyu Zhao , Shaofeng Zhang , Xiaoxing Wang , Yifan Yang , Junchi Yan , Xue Yang

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge…

计算机视觉与模式识别 · 计算机科学 2024-11-08 Qingsong Xie , Zhenyi Liao , Zhijie Deng , Chen chen , Haonan Lu

Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Ze Wang , Hao Chen , Benran Hu , Jiang Liu , Ximeng Sun , Jialian Wu , Yusheng Su , Xiaodong Yu , Emad Barsoum , Zicheng Liu

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

计算机视觉与模式识别 · 计算机科学 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Zirui Wang , Zhizhou Sha , Zheng Ding , Yilin Wang , Zhuowen Tu

Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Yawen Yang , Feng Li , Shuqi Kong , Yunfeng Diao , Xinjian Gao , Zenglin Shi , Meng Wang

This technical report introduces PIXART-{\delta}, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-{\alpha} model. PIXART-{\alpha} is recognized for its ability…

计算机视觉与模式识别 · 计算机科学 2024-01-11 Junsong Chen , Yue Wu , Simian Luo , Enze Xie , Sayak Paul , Ping Luo , Hang Zhao , Zhenguo Li

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Maitreya Patel , Jingtao Li , Weiming Zhuang , Yezhou Yang , Lingjuan Lv

Flow matching and diffusion models have shown impressive results in text-to-image generation, producing photorealistic images through an iterative denoising process. A common strategy to speed up synthesis is to perform early denoising at…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Jyun-Ze Tang , Chih-Fan Hsu , Jeng-Lin Li , Ming-Ching Chang , Wei-Chao Chen

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization,…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Roman Bachmann , Jesse Allardice , David Mizrahi , Enrico Fini , Oğuzhan Fatih Kar , Elmira Amirloo , Alaaeldin El-Nouby , Amir Zamir , Afshin Dehghan

Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Hengyu Zeng , Xin Gao , Guanghao Li , Yuxiang Yan , Jiaoyang Ruan , Junpeng Ma , Haoyu Albert Wang , Jian Pu

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Shivam Duggal , Xingjian Bai , Zongze Wu , Richard Zhang , Eli Shechtman , Antonio Torralba , Phillip Isola , William T. Freeman
‹ 上一页 1 2 3 10 下一页 ›