中文
相关论文

相关论文: Intrinsic Dynamic Shape Prior for Fast, Sequential…

200 篇论文

We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Zhengdi Yu , Simone Foti , Linguang Zhang , Amy Zhao , Cem Keskin , Stefanos Zafeiriou , Tolga Birdal

Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Remi Chierchia , Léo Lebrat , David Ahmedt-Aristizabal , Olivier Salvado , Clinton Fookes , Rodrigo Santa Cruz

Fast convergence and high-quality image recovery are two essential features of algorithms for solving ill-posed imaging inverse problems. Existing methods, such as regularization by denoising (RED), often focus on designing sophisticated…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Marien Renaud , Julien Hermant , Deliang Wei , Yu Sun

Neural implicit surface reconstruction using volume rendering techniques has recently achieved significant advancements in creating high-fidelity surfaces from multiple 2D images. However, current methods primarily target scenes with…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Lintao Xiang , Hongpei Zheng , Bailin Deng , Hujun Yin

Accurately capturing the full-range response of structures is crucial in structural health monitoring (SHM) for ensuring safety and operational integrity. However, limited sensor deployment due to cost, accessibility, or scale often hinders…

计算工程、金融与科学 · 计算机科学 2025-09-25 Wingho Feng , Quanwang Li , Chen Wang , Jian-sheng Fan

Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem which often requires prior…

图像与视频处理 · 电气工程与系统科学 2022-06-09 Chen Qin , Shuo Wang , Chen Chen , Wenjia Bai , Daniel Rueckert

Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scene modeling, obtaining high-fidelity rendering and accurate…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yinan Deng , Jianyu Dou , Jiahui Wang , Jingyu Zhao , Yi Yang , Yufeng Yue

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Ying Zang , Yidong Han , Chaotao Ding , Yuanqi Hu , Deyi Ji , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

Purpose: To accelerate MRI acquisition by incorporating the previous scans of a subject during reconstruction. Although longitudinal imaging constitutes much of clinical MRI, leveraging previous scans is challenging due to the complex…

图像与视频处理 · 电气工程与系统科学 2025-10-21 Yonatan Urman , Zachary Shah , Ashwin Kumar , Bruno P. Soares , Kawin Setsompop

Diffusion-based image super-resolution (SR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) observations. However, the inherent randomness injected during the reverse diffusion process causes the performance of…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Shuwei Huang , Shizhuo Liu , Zijun Wei

Magnetic resonance fingerprinting (MRF) provides a unique concept for simultaneous and fast acquisition of multiple quantitative MR parameters. Despite acquisition efficiency, adoption of MRF into the clinics is hindered by its dictionary…

图像与视频处理 · 电气工程与系统科学 2020-08-11 Fabian Balsiger , Alain Jungo , Olivier Scheidegger , Pierre G. Carlier , Mauricio Reyes , Benjamin Marty

Intraoperative navigation relies heavily on precise 3D reconstruction to ensure accuracy and safety during surgical procedures. However, endoscopic scenarios present unique challenges, including sparse features and inconsistent lighting,…

图形学 · 计算机科学 2025-07-17 Yuchao Zheng , Jianing Zhang , Guochen Ning , Hongen Liao

Diverse human motion prediction (HMP) aims to predict multiple plausible future motions given an observed human motion sequence. It is a challenging task due to the diversity of potential human motions while ensuring an accurate description…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Hua Yu , Yaqing Hou , Wenbin Pei , Qiang Zhang

Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details.…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Xinyuan Hu , Changyue Shi , Chuxiao Yang , Minghao Chen , Jiajun Ding , Tao Wei , Chen Wei , Zhou Yu , Min Tan

3D neural implicit representations play a significant component in many robotic applications. However, reconstructing neural radiance fields (NeRF) from realistic event data remains a challenge due to the sparsities and the lack of…

机器人学 · 计算机科学 2024-01-31 Jiaxu Wang , Junhao He , Ziyi Zhang , Renjing Xu

We introduce a generative smoothness regularization on manifolds (SToRM) model for the recovery of dynamic image data from highly undersampled measurements. The model assumes that the images in the dataset are non-linear mappings of…

图像与视频处理 · 电气工程与系统科学 2021-03-12 Qing Zou , Abdul Haseeb Ahmed , Prashant Nagpal , Stanley Kruger , Mathews Jacob

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal…

计算机视觉与模式识别 · 计算机科学 2024-11-15 Hojun Jang , Young Min Kim

Recent advancements in Neural Surface Reconstruction (NSR) have significantly improved multi-view reconstruction when coupled with volume rendering. However, relying solely on photometric consistency in image space falls short of addressing…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Xinlin Ren , Chenjie Cao , Yanwei Fu , Xiangyang Xue

Sequential Recommendation (SR) characterizes evolving patterns of user behaviors by modeling how users transit among items. However, the short interaction sequences limit the performance of existing SR. To solve this problem, we focus on…

信息检索 · 计算机科学 2022-09-22 Xiaolin Zheng , Jiajie Su , Weiming Liu , Chaochao Chen

Many imaging science tasks can be modeled as a discrete linear inverse problem. Solving linear inverse problems is often challenging, with ill-conditioned operators and potentially non-unique solutions. Embedding prior knowledge, such as…

数值分析 · 数学 2023-12-07 Elizabeth Newman , Jack Michael Solomon , Matthias Chung
‹ 上一页 1 8 9 10 下一页 ›