中文
相关论文

相关论文: Inference-time Stochastic Refinement of GRU-Normal…

200 篇论文

Predicting depth from a monocular video sequence is an important task for autonomous driving. Although it has advanced considerably in the past few years, recent methods based on convolutional neural networks (CNNs) discard temporal…

计算机视觉与模式识别 · 计算机科学 2019-09-17 Chanho Eom , Hyunjong Park , Bumsub Ham

We propose an inference-time scaling approach for pretrained flow models. Recently, inference-time scaling has gained significant attention in LLMs and diffusion models, improving sample quality or better aligning outputs with user…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Jaihoon Kim , Taehoon Yoon , Jisung Hwang , Minhyuk Sung

Invertible convolutions have been an essential element for building expressive normalizing flow-based generative models since their introduction in Glow. Several attempts have been made to design invertible $k \times k$ convolutions that…

计算机视觉与模式识别 · 计算机科学 2023-01-24 Aditya Kallappa , Sandeep Nagar , Girish Varma

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Yusuf Shihata

Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…

计算机视觉与模式识别 · 计算机科学 2024-11-15 Zhiyang Lu , Qinghan Chen , Ming Cheng

The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Zikai Zhou , Muyao Wang , Shitong Shao , Lichen Bai , Haoyi Xiong , Bo Han , Zeke Xie

Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFPN, a novel architecture that harnesses the synergy between…

图像与视频处理 · 电气工程与系统科学 2025-03-17 M. Akın Yılmaz , Ahmet Bilican , A. Murat Tekalp

Traffic flow forecasting is essential for managing congestion, improving safety, and optimizing various transportation systems. However, it remains a prevailing challenge due to the stochastic nature of urban traffic and environmental…

机器学习 · 计算机科学 2025-09-16 Mayur Patil , Qadeer Ahmed , Shawn Midlam-Mohler

Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise.…

计算机视觉与模式识别 · 计算机科学 2024-03-06 Robert Mendel , Tobias Rueckert , Dirk Wilhelm , Daniel Rueckert , Christoph Palm

Channel estimation is a fundamental challenge in massive multiple-input multiple-output systems, where estimation accuracy governs the spectral efficiency and link reliability. In this work, we introduce Recursive Flow (RC-Flow), a novel…

Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Qianang Zhou , Zhiyu Zhu , Junhui Hou , Yongjian Deng , Youfu Li , Junlin Xiong

Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Swathikiran Sudhakaran , Sergio Escalera , Oswald Lanz

Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the…

计算机视觉与模式识别 · 计算机科学 2018-03-19 Marc Oliu , Javier Selva , Sergio Escalera

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…

机器学习 · 计算机科学 2026-05-29 Junru Zhang , Lang Feng , Jinbo Wang , Xu Guo , Yucheng Wang , Han Yu , Min Wu , Yabo Dong , Duanqing Xu

Bayesian inference in the physical sciences faces a fundamental challenge: the imperative for high-fidelity physical modeling often clashes with the intrinsic limitations of stochastic sampling algorithms. Complex, high-dimensional…

天体物理仪器与方法 · 物理学 2026-04-09 Bo Liang , Chang Liu , Hanlin Song , Tianyu Zhao , Minghui Du , He Wang , Haohao Gu , Sensen He , Yuxiang Xu , Wei-Liang Qian , Li-e Qiang , Peng Xu , Ziren Luo , Mingming Sun

Fueled by the expressive power of deep neural networks, normalizing flows have achieved spectacular success in generative modeling, or learning to draw new samples from a distribution given a finite dataset of training samples. Normalizing…

机器学习 · 计算机科学 2023-05-05 Yuehaw Khoo , Michael Lindsey , Hongli Zhao

We propose a flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video inpainting. More specially, we design a novel flow…

计算机视觉与模式识别 · 计算机科学 2022-08-16 Kaidong Zhang , Jingjing Fu , Dong Liu

Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving. Despite their success, the underlying reasons for their astonishing…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Dongrui Liu , Daqi Liu , Xueqian Li , Sihao Lin , Hongwei xie , Bing Wang , Xiaojun Chang , Lei Chu

Accurate and refined passenger flow prediction is essential for optimizing the collaborative management of multiple collection and distribution modes in large-scale transportation hubs. Traditional methods often focus only on the overall…

机器学习 · 计算机科学 2025-04-10 Ronghui Zhang , Wenbin Xing , Mengran Li , Zihan Wang , Junzhou Chen , Xiaolei Ma , Zhiyuan Liu , Zhengbing He

We introduce VideoFlow, a novel optical flow estimation framework for videos. In contrast to previous methods that learn to estimate optical flow from two frames, VideoFlow concurrently estimates bi-directional optical flows for multiple…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Xiaoyu Shi , Zhaoyang Huang , Weikang Bian , Dasong Li , Manyuan Zhang , Ka Chun Cheung , Simon See , Hongwei Qin , Jifeng Dai , Hongsheng Li