Results 31 to 40 of about 7,539,459 (382)
PU-Dense: Sparse Tensor-Based Point Cloud Geometry Upsampling
IEEE Transactions on Image Processing, 2022 Due to the increased popularity of augmented and virtual reality experiences, the interest in capturing high-resolution real-world point clouds has never been higher.
Anique Akhtar +4 more
semanticscholar +1 more source
International Journal of Adaptive Control and Signal Processing, EarlyView., 2023 Summary In this contribution, we propose a detailed study of interpolation‐based data‐driven methods that are of relevance in the model reduction and also in the systems and control communities. The data are given by samples of the transfer function of the underlying (unknown) model, that is, we analyze frequency‐response data.
Quirin Aumann, Ion Victor Gosea
wiley +1 more source
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [PDF]
AAAI Conference on Artificial Intelligence, 2020 In 2D image processing, some attempts decompose images into high and low frequency components for describing edge and smooth parts respectively. Similarly, the contour and flat area of 3D objects, such as the boundary and seat area of a chair, describe ...
Mutian Xu +5 more
semanticscholar +1 more source
Layered Projection-Based Quality Assessment of 3D Point Clouds
IEEE Access, 2021 Point clouds are subject to various distortions during point cloud processing missions, any of which may lead to quality degradation. Consequently, predicting point cloud quality has attracted a lot of attention. In this paper, a layered projection-based
Tianxin Chen +7 more
doaj +1 more source
A Point-to-Distribution Joint Geometry and Color Metric for Point Cloud Quality Assessment [PDF]
IEEE International Workshop on Multimedia Signal Processing, 2021 Point clouds (PCs) are a powerful 3D visual representation paradigm for many emerging application domains, especially virtual and augmented reality, and autonomous vehicles. However, the large amount of PC data required for highly immersive and realistic
Alireza Javaheri +3 more
semanticscholar +1 more source
Geometry-Informed Neural Operator for Large-Scale 3D PDEs [PDF]
Neural Information Processing Systems, 2023 We propose the geometry-informed neural operator (GINO), a highly efficient approach to learning the solution operator of large-scale partial differential equations with varying geometries.
Zong-Yi Li +10 more
semanticscholar +1 more source
Pairwise transitive 2-designs [PDF]
, 2015 We classify the pairwise transitive 2-designs, that is, 2-designs such that a group of automorphisms is transitive on the following five sets of ordered pairs: point-pairs, incident point-block pairs, non-incident point-block pairs, intersecting block ...
Devillers, Alice, Praeger, Cheryl E.
core +1 more source
Patch-Based Deep Autoencoder for Point Cloud Geometry Compression [PDF]
ACM Multimedia Asia, 2021 The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry compression.
Kang-Soo You, Pan Gao
semanticscholar +1 more source
Dynamic Point Cloud Compression Based on Projections, Surface Reconstruction and Video Compression
Sensors, 2021 In this paper we will present a new dynamic point cloud compression based on different projection types and bit depth, combined with the surface reconstruction algorithm and video compression for obtained geometry and texture maps. Texture maps have been
Emil Dumic +2 more
doaj +1 more source
The geometry of degenerations of Hilbert schemes of points [PDF]
Journal of Algebraic Geometry, 2020 Given a strict simple degenerationf:X→Cf \colon X\to Cthe first three authors previously constructed a degenerationIX/Cn→CI^n_{X/C} \to Cof the relative degreennHilbert scheme of00-dimensional subschemes. In this paper we investigate the geometry of this degeneration, in particular when the fibre dimension offfis at most22.
Lars Halvard Halle +4 more
openaire +6 more sources