English
Related papers

Related papers: VDE: Training-Free Accelerating Rectified Flow Mod…

200 papers

Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Feiyang Chen , Ziqian Luo , Lisang Zhou , Xueting Pan , Ying Jiang

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Jaihyun Lew , Jooyoung Choi , Chaehun Shin , Dahuin Jung , Sungroh Yoon

Extracting information on fluid motion directly from images is challenging. Fluid flow represents a complex dynamic system governed by the Navier-Stokes equations. General optical flow methods are typically designed for rigid body motion,…

Machine Learning · Computer Science 2022-06-23 Mingrui Zhang , Jianhong Wang , James Tlhomole , Matthew D. Piggott

We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Tuan Duc Ngo , Ashkan Mirzaei , Guocheng Qian , Hanwen Liang , Chuang Gan , Evangelos Kalogerakis , Peter Wonka , Chaoyang Wang

Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Zhanzhong Pang , Dibyadip Chatterjee , Fadime Sener , Angela Yao

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Komal Kumar , Rao Muhammad Anwer , Fahad Shahbaz Khan , Salman Khan , Ivan Laptev , Hisham Cholakkal

Statistical surrogate modeling of fluid flows is hard because dynamics are multiscale and highly sensitive to initial conditions. Conditional diffusion surrogates can be accurate, but usually need hundreds of stochastic sampling steps. We…

Machine Learning · Computer Science 2026-02-10 Victor Armegioiu , Yannick Ramic , Siddhartha Mishra

Monocular depth estimation (MDE) has widely applicable but remains highly challenging due to the inherently ill-posed nature of reconstructing 3D scenes from single 2D images. Modern Vision Foundation Models (VFMs), pre-trained on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Gongshu Wang , Zhirui Wang , Kan Yang

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature caching offers a promising training-free acceleration solution by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Fanpu Cao , Yaofo Chen , Zeng You , Wei Luo

The rapid advancement of generative models has led to a growing prevalence of highly realistic AI-generated images, posing significant challenges for digital forensics and content authentication. Conventional detection methods mainly rely…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Dabbrata Das , Mahshar Yahan , Md Tareq Zaman , Md Rishadul Bayesh

Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

We present two a posteriori error estimators for the virtual element method (VEM) based on global and local flux reconstruction in the spirit of [5]. The proposed error estimators are reliable and efficient for the $h$-, $p$-, and…

Numerical Analysis · Mathematics 2025-03-14 F. Dassi , J. Gedicke , L. Mascotto

We propose an image-based flow decomposition developed from the two-dimensional (2D) tensor empirical wavelet transform (EWT) (Gilles 2013). The idea is to decompose the instantaneous flow data, or its visualisation, adaptively according to…

Fluid Dynamics · Physics 2020-12-24 Jie Ren , Xuerui Mao , Song Fu

3D particle tracking velocimetry (PTV) is a key technique for analyzing turbulent flow, one of the most challenging computational problems of our century. At the core of 3D PTV is the dual-frame fluid motion estimation algorithm, which…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Yifei Zhang , Huan-ang Gao , Zhou Jiang , Hao Zhao

The future of high-performance computing, specifically on future Exascale computers, will presumably see memory capacity and bandwidth fail to keep pace with data generated, for instance, from massively parallel partial differential…

Computational Physics · Physics 2020-01-29 Alec M. Dunton , Lluís Jofre , Gianluca Iaccarino , Alireza Doostan

Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Qiaole Dong , Bo Zhao , Yanwei Fu

In high-energy physics, precise measurements rely on highly reliable detector simulations. Traditionally, these simulations involve incorporating experiment data to model detector responses and fine-tuning them. However, due to the…

High Energy Physics - Experiment · Physics 2024-01-08 Wenxing Fang , Weidong Li , Xiaobin Ji , Shengsen Sun , Tong Chen , Fang Liu , Xiaoling Li , Kai Zhu , Tao Lin , Jinfa Qiu

Models play an important role in inverse problems, serving as the prior for representing the original signal to be recovered. REgularization by Denoising (RED) is a recently introduced general framework for constructing such priors using…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Tao Hong , Yaniv Romano , Michael Elad

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Lujie Xia , Ziluo Ding , Rui Zhao , Jiyuan Zhang , Lei Ma , Zhaofei Yu , Tiejun Huang , Ruiqin Xiong

In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Xuezhe Ma , Xiang Kong , Shanghang Zhang , Eduard Hovy
‹ Prev 1 8 9 10 Next ›