English
Related papers

Related papers: DIFT: Dynamic Iterative Field Transforms for Memor…

200 papers

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Zihua Zheng , Ni Nie , Zhi Ling , Pengfei Xiong , Jiangyu Liu , Hao Wang , Jiankun Li

The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation. However, their memory consumption increases quadratically with input…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Gangwei Xu , Shujun Chen , Hao Jia , Miaojie Feng , Xin Yang

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Daikun Liu , Lei Cheng , Teng Wang , changyin Sun

We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost. This design…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Yihan Wang , Jia Deng

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Kai Wang , Yibing Song , Gao Huang , Fan Wang , Yang You

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Kai Wang , Hao Luo , Yibing Song , Gao Huang , Fan Wang , Yang You

Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Navid Eslami , Farnoosh Arefi , Amir M. Mansourian , Shohreh Kasaei

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Kunpeng Du , Haizhen Xie , Sen Lu , Lei Yu , Binglei Bao , Huaao Tang , Chuntao Liu , Hao Wu , Yang Zhao , Zhicai Huang , Heyuan Gao , Zhijun Tu , Jie Hu , Xinghao Chen

We present CompactFlowNet, the first real-time mobile neural network for optical flow prediction, which involves determining the displacement of each pixel in an initial frame relative to the corresponding pixel in a subsequent frame.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Andrei Znobishchev , Valerii Filev , Oleg Kudashev , Nikita Orlov , Humphrey Shi

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Wangbo Zhao , Jiasheng Tang , Yizeng Han , Yibing Song , Kai Wang , Gao Huang , Fan Wang , Yang You

Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation. However, fine-tuning these models requires substantial computational complexity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Sunghyun Park , Jeongho Kim , Hyoungwoo Park , Debasmit Das , Sungrack Yun , Munawar Hayat , Jaegul Choo , Fatih Porikli , Seokeon Choi

Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow…

Computer Vision and Pattern Recognition · Computer Science 2024-01-08 Ri Cheng , Ruian He , Xuhao Jiang , Shili Zhou , Weimin Tan , Bo Yan

The cost volume, capturing the similarity of possible correspondences across two input images, is a key ingredient in state-of-the-art optical flow approaches. When sampling correspondences to build the cost volume, a large neighborhood…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Huaizu Jiang , Erik Learned-Miller

Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly across input spatial tokens, wasting resource allocation to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Moayed Haji-Ali , Willi Menapace , Ivan Skorokhodov , Dogyun Park , Anil Kag , Michael Vasilkovsky , Sergey Tulyakov , Vicente Ordonez , Aliaksandr Siarohin

Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Liubing Hu , Chen Wu , Anrui Wang , Dianjie Lu , Guijuan Zhang , Zhuoran Zheng

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

Hardware Architecture · Computer Science 2026-04-13 Jinqi Wen , Tong Xie , Runsheng Wang , Meng Li

Cost volumes are used in every modern optical flow estimator, but due to their computational and space complexity, they are often a limiting factor regarding both processing speed and the resolution of input frames. Motivated by our…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Simon Kiefhaber , Stefan Roth , Simone Schaub-Meyer

Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving small objects. The…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Dianbo Ma , Kousuke Imamura , Ziyan Gao , Xiangjie Wang , Satoshi Yamane

Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variations in the spatial scale and difficulties of recognition…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Yuchen Ma , Zhengcong Fei , Junshi Huang

Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in the number of pixels. Although an alternative…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Karlis Martins Briedis , Markus Gross , Christopher Schroers
‹ Prev 1 2 3 10 Next ›