中文
相关论文

相关论文: Non-Euclidean interfaces decode the continuous lan…

200 篇论文

Despite many studies on how geometry can be used to control the electronic properties of graphene, certain limitations to fabrication of designed graphene nanostructures exist. Here, we demonstrate controlled topographical replication of…

介观与纳米尺度物理 · 物理学 2015-06-19 Y. Moon , J. Shin , S. Seo , J. Park , S. R. Dugasani , S. H. Woo , T. Park , S. H. Park , J. R. Ahn

Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the…

机器学习 · 计算机科学 2022-11-03 Ashish Tiwari , Sresth Tosniwal , Shanmuganathan Raman

Control of nucleation sites is an important goal in materials growth: nuclei in regular arrays may show emergent photonic or electronic behavior, and once the nuclei coalesce into thin films, the nucleation density influences parameters…

Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database. The main roadblock of building a large-scale face model from diverse 3D databases lies in the lack of dense…

计算机视觉与模式识别 · 计算机科学 2019-08-15 Feng Liu , Luan Tran , Xiaoming Liu

Two-phase flow phenomena underpin critical technologies such as hydrogen fuel cells, spray cooling, and combustion, where droplet dynamics govern performance and efficiency. Conventional optical diagnostics, including shadowgraphy and…

流体动力学 · 物理学 2025-11-27 Maximilian Dreisbach , Elham Kiyani , Jochen Kriegseis , George Karniadakis , Alexander Stroh

Understanding structure-property relationships in complex materials requires integrating complementary measurements across multiple length scales. Here we propose an interpretable "multimodal" machine learning framework that unifies…

材料科学 · 物理学 2026-02-03 Shun Muroga , Hideaki Nakajima , Taiyo Shimizu , Kazufumi Kobashi , Kenji Hata

van der Waals (vdW) epitaxy is conventionally regarded as a rotation-free and strain-free growth mode driven by weak, isotropic interactions, yet many interfaces paradoxically exhibit strictly locked orientations that defy standard…

材料科学 · 物理学 2025-12-29 Renhong Liang , Mao Ye , Renkui Zheng , Jianhua Hao , Haitao Huang , Longlong Shu , Shanming Ke

The ability to change a surface's profile allows biological systems to effectively manipulate and blend into their surroundings. Current surface morphing techniques rely either on having a small number of fixed states or on directly driving…

机器人学 · 计算机科学 2021-12-17 Sawyer Thomas , Jeffrey Lipton

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…

计算机视觉与模式识别 · 计算机科学 2018-08-22 Dario Rethage , Federico Tombari , Felix Achilles , Nassir Navab

We proposed a generalized method, NeuralSSD, for reconstructing a 3D implicit surface from the widely-available point cloud data. NeuralSSD is a solver-based on the neural Galerkin method, aimed at reconstructing higher-quality and accurate…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Zi-Chen Xi , Jiahui Huang , Hao-Xiang Chen , Francis Williams , Qun-Ce Xu , Tai-Jiang Mu , Shi-Min Hu

Reconstructing open surfaces from multi-view images is vital in digitalizing complex objects in daily life. A widely used strategy is to learn unsigned distance functions (UDFs) by checking if their appearance conforms to the image…

计算机视觉与模式识别 · 计算机科学 2025-03-31 Shujuan Li , Yu-Shen Liu , Zhizhong Han

Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to…

计算机视觉与模式识别 · 计算机科学 2019-02-01 Edward J. Smith , Scott Fujimoto , Adriana Romero , David Meger

We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve…

机器学习 · 计算机科学 2023-11-21 Chaoran Cheng , Jian Peng

Mesh-based learning is one of the popular approaches nowadays to learn shapes. The most established backbone in this field is MeshCNN. In this paper, we propose infusing MeshCNN with geometric reasoning to achieve higher quality learning.…

图形学 · 计算机科学 2021-05-28 Amir Barda , Yotam Erel , Amit H. Bermano

We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects. Our method builds in a novel way on concepts from…

计算机视觉与模式识别 · 计算机科学 2020-12-08 David Novotny , Roman Shapovalov , Andrea Vedaldi

Neural implicit functions have emerged as a powerful representation for surfaces in 3D. Such a function can encode a high quality surface with intricate details into the parameters of a deep neural network. However, optimizing for the…

计算机视觉与模式识别 · 计算机科学 2021-04-13 Wang Yifan , Shihao Wu , Cengiz Oztireli , Olga Sorkine-Hornung

Spectral functions play a central role in the characterization of a wide range of physical systems, including strongly interacting quantum field theories and many-body systems. Their non-perturbative determination from Euclidean correlation…

高能物理 - 格点 · 物理学 2026-04-16 Norikazu Yamada

Disclinations are ubiquitous lattice defects existing in almost all crystalline materials. In two-dimensional nanomaterials, disclinations lead to the warping and deformation of the hosting material, yielding non-Euclidean geometries.…

介观与纳米尺度物理 · 物理学 2022-01-26 Ying Chen , Yuhang Yin , Ze-Huan Zheng , Yang Liu , Zhi-Kang Lin , Jing Li , Jian-Hua Jiang , Huanyang Chen

Convolutional Neural Networks (CNNs) have been providing the state-of-the-art performance for learning-related problems involving 2D/3D images in Euclidean space. However, unlike in the Euclidean space, the shapes of many structures in…

计算机视觉与模式识别 · 计算机科学 2019-04-02 Fenqiang Zhao , Shunren Xia , Zhengwang Wu , Dingna Duan , Li Wang , Weili Lin , John H Gilmore , Dinggang Shen , Gang Li

Two-dimensional (2D) layered nanomaterials heterostructures, arising from the combination of 2D materials with other low-dimensional species, feature large surface area to volume ratio, which provides a high density of active sites for…

材料科学 · 物理学 2025-02-19 Mengjiao Wang , Michal Langer , Roberto Altieri , Matteo Crisci , Silvio Osella , Teresa Gatti
‹ 上一页 1 8 9 10 下一页 ›