Advances in neural rendering
Synthesizing photo‐realistic images and videos is at the heart of computer graphics and has
been the focus of decades of research. Traditionally, synthetic images of a scene are …
been the focus of decades of research. Traditionally, synthetic images of a scene are …
Mixture of volumetric primitives for efficient neural rendering
Real-time rendering and animation of humans is a core function in games, movies, and
telepresence applications. Existing methods have a number of drawbacks we aim to …
telepresence applications. Existing methods have a number of drawbacks we aim to …
A review on deep learning approaches for 3D data representations in retrieval and classifications
AS Gezawa, Y Zhang, Q Wang, L Yunqi - IEEE access, 2020 - ieeexplore.ieee.org
Deep learning approach has been used extensively in image analysis tasks. However,
implementing the methods in 3D data is a bit complex because most of the previously …
implementing the methods in 3D data is a bit complex because most of the previously …
Geometric back-projection network for point cloud classification
As the basic task of point cloud analysis, classification is fundamental but always
challenging. To address some unsolved problems of existing methods, we propose a …
challenging. To address some unsolved problems of existing methods, we propose a …
Transfer learning from synthetic to real lidar point cloud for semantic segmentation
Abstract Knowledge transfer from synthetic to real data has been widely studied to mitigate
data annotation constraints in various computer vision tasks such as semantic segmentation …
data annotation constraints in various computer vision tasks such as semantic segmentation …
[HTML][HTML] Point cloud semantic segmentation using a deep learning framework for cultural heritage
In the Digital Cultural Heritage (DCH) domain, the semantic segmentation of 3D Point
Clouds with Deep Learning (DL) techniques can help to recognize historical architectural …
Clouds with Deep Learning (DL) techniques can help to recognize historical architectural …
Differentiable surface splatting for point-based geometry processing
We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for
point clouds. Gradients for point locations and normals are carefully designed to handle …
point clouds. Gradients for point locations and normals are carefully designed to handle …
A survey on deep learning advances on different 3D data representations
E Ahmed, A Saint, AER Shabayek… - arXiv preprint arXiv …, 2018 - arxiv.org
3D data is a valuable asset the computer vision filed as it provides rich information about the
full geometry of sensed objects and scenes. Recently, with the availability of both large 3D …
full geometry of sensed objects and scenes. Recently, with the availability of both large 3D …
Point attention network for semantic segmentation of 3D point clouds
Abstract Convolutional Neural Networks (CNNs) have performed extremely well on data
represented by regularly arranged grids such as images. However, directly leveraging the …
represented by regularly arranged grids such as images. However, directly leveraging the …
Pulsar: Efficient sphere-based neural rendering
C Lassner, M Zollhofer - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
We propose Pulsar, an efficient sphere-based differentiable rendering module that is orders
of magnitude faster than competing techniques, modular, and easy-to-use due to its tight …
of magnitude faster than competing techniques, modular, and easy-to-use due to its tight …