English
Related papers

Related papers: Adapting VACE for Real-Time Autoregressive Video D…

200 papers

Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Taesung Kwon , Jonghyun Park , Hyungjin Chung , Jong Chul Ye

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yazhou Xing , Yang Fei , Yingqing He , Jingye Chen , Jiaxin Xie , Xiaowei Chi , Qifeng Chen

Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Liuhan Chen , Zongjian Li , Bin Lin , Bin Zhu , Qian Wang , Shenghai Yuan , Xing Zhou , Xinhua Cheng , Li Yuan

A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Kunyang Li , Mubarak Shah , Yuzhang Shang

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Wentai Zhang , Ronghui Xi , Shiyao Peng , Jiayu Huang , Haoran Luo , Zichen Tang , Haihong E

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Kumara Kahatapitiya , Adil Karjauv , Davide Abati , Fatih Porikli , Yuki M. Asano , Amirhossein Habibian

Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Rui Xie , Tianchen Zhao , Zhihang Yuan , Rui Wan , Wenxi Gao , Zhenhua Zhu , Xuefei Ning , Yu Wang

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames increases, the memory consumption for training and inference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Jia Wang , Xinfeng Zhang , Gai Zhang , Jun Zhu , Lv Tang , Li Zhang

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Sheng Li , Yang Sui , Junhao Ran , Bo Yuan , Yue Dai , Xulong Tang

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Desai Xie , Zhan Xu , Yicong Hong , Hao Tan , Difan Liu , Feng Liu , Arie Kaufman , Yang Zhou

Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Sijie Zhao , Yong Zhang , Xiaodong Cun , Shaoshu Yang , Muyao Niu , Xiaoyu Li , Wenbo Hu , Ying Shan

Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Jianbiao Mei , Tao Hu , Xuemeng Yang , Licheng Wen , Yu Yang , Tiantian Wei , Yukai Ma , Min Dou , Botian Shi , Yong Liu

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Zhening Xing , Gereon Fox , Yanhong Zeng , Xingang Pan , Mohamed Elgharib , Christian Theobalt , Kai Chen

Recent advancements in diffusion-based models have demonstrated significant success in generating images from text. However, video editing models have not yet reached the same level of visual quality and user control. To address this, we…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Ozgur Kara , Bariscan Kurtkaya , Hidir Yesiltepe , James M. Rehg , Pinar Yanardag

Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse attention methods degrade under high sparsity. We show empirically that generation quality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Shihao Han , Hao Yang , Xinting Hu , Xiaofeng Mei , Yi Jiang , Xiaojuan Qi

Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Hidir Yesiltepe , Tuna Han Salih Meral , Adil Kaan Akan , Kaan Oktay , Pinar Yanardag

Even though large-scale text-to-image generative models show promising performance in synthesizing high-quality images, applying these models directly to image editing remains a significant challenge. This challenge is further amplified in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-03 Shutong Jin , Ruiyu Wang , Florian T. Pokorny