English
Related papers

Related papers: Sparse VideoGen2: Accelerate Video Generation with…

200 papers

Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet standard variable-length attention APIs -- including FlashAttention-2's varlen and PyTorch's…

Machine Learning · Computer Science 2026-05-13 Seifeldin Abdellatif , Ahmad Almasri

Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Haotang Li , Zhenyu Qi , Shaohan Henry Wang , Kebin Peng , Zi Wang , Qing Guo , Sen He , Huanrui Yang

Controllable video generation aims to synthesize video content that aligns precisely with user-provided conditions, such as text descriptions and initial images. However, a significant challenge persists in this domain: existing models…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Peng Hu , Yu Gu , Liang Luo , Fuji Ren

Text-to-video (T2V) synthesis models, such as OpenAI's Sora, have garnered significant attention due to their ability to generate high-quality videos from a text prompt. In diffusion-based T2V models, the attention mechanism is a critical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Bingyan Liu , Chengyu Wang , Tongtong Su , Huan Ten , Jun Huang , Kailing Guo , Kui Jia

Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities to generate diverse and high-quality images. However, leveraging their potential for real-world content creation,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Sandra Zhang Ding , Jiafeng Mao , Kiyoharu Aizawa

The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Qihang Fan , Huaibo Huang , Mingrui Chen , Ran He

Leveraging text, images, structure maps, or motion trajectories as conditional guidance, diffusion models have achieved great success in automated and high-quality video generation. However, generating smooth and rational transition videos…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zuhao Yang , Jiahui Zhang , Yingchen Yu , Shijian Lu , Song Bai

Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transformers. However, existing hardware accelerators lack support…

Hardware Architecture · Computer Science 2025-05-20 Tenglong Li , Jindong Li , Guobin Shen , Dongcheng Zhao , Qian Zhang , Yi Zeng

Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Mingde Zhou , Zheng Chen , Yulun Zhang

Vision Transformers have substantially advanced the capabilities of segmentation models across both image and video domains. Among them, the Swin Transformer stands out for its ability to capture hierarchical, multi-scale representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Ka-Wai Yung , Felix J. S. Bragman , Jialang Xu , Imanol Luengo , Danail Stoyanov , Evangelos B. Mazomenos

Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Minghong Cai , Xiaodong Cun , Xiaoyu Li , Wenze Liu , Zhaoyang Zhang , Yong Zhang , Ying Shan , Xiangyu Yue

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Ivan Skorokhodov , Sergey Tulyakov , Mohamed Elhoseiny

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Quang Nguyen , Truong Vu , Anh Tran , Khoi Nguyen

Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Alireza Zareian , Svebor Karaman , Shih-Fu Chang

Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 945 seconds of total…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Peiyuan Zhang , Yongqi Chen , Runlong Su , Hangliang Ding , Ion Stoica , Zhengzhong Liu , Hao Zhang

3D Gaussian splatting (3DGS) is an innovative rendering technique that surpasses the neural radiance field (NeRF) in both rendering speed and visual quality by leveraging an explicit 3D scene representation. Existing 3DGS approaches require…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Lintao Xiang , Hongpei Zheng , Yating Huang , Qijun Yang , Hujun Yin

High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 YaoYang Liu , Yuechen Zhang , Wenbo Li , Yufei Zhao , Rui Liu , Long Chen

Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Guantao Chen , Shikang Zheng , Yuqi Lin , Linfeng Zhang

The Vision Transformer (ViT) has achieved notable success in computer vision, with its variants widely validated across various downstream tasks, including semantic segmentation. However, as general-purpose visual encoders, ViT backbones…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Guoan Xu , Jiaming Chen , Wenfeng Huang , Wenjing Jia , Guangwei Gao , Guo-Jun Qi
‹ Prev 1 8 9 10 Next ›