A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
How Powerful Are Randomly Initialized Pointcloud Set Functions?
[article]
2020
arXiv
pre-print
Preserved Fulltext
We study random embeddings produced by untrained neural set functions, and show that they are powerful representations which well capture the input features for downstream tasks such as classification, ...
We obtain surprising results that show that random set functions can often obtain close to or even better accuracy than fully trained models. ...
In this work, we study randomly initialized set functions, particularly for pointclouds in a similar vein, and make the following contributions: First, we experiment with well known set-based neural networks ...
arXiv:2003.05410v1
fatcat:ttfl35wahve3tcv2lxq4mk34my
Intrinsic Neural Fields: Learning Functions on Manifolds
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2203.07967v2 fatcat:lbaqoyoorvelbj57n7rvfxt2wyOther Versions
The extrinsic embedding ignores known intrinsic manifold properties and is inflexible wrt. transfer of the learned function. ...
Some of their advantages are a sound theoretic foundation and an easy implementation in current deep learning frameworks. ...
Specifically, potential background pixels are identified based on their intensity due to the mostly white background. They are removed if they are close to the boundary of the initial mask. ...
arXiv:2203.07967v3
fatcat:2rxv6eedp5cxzlp2beoiojswna
Texture Fields: Learning Texture Representations in Function Space
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network. ...
We show that Texture Fields are able to represent high frequency texture and naturally blend with modern deep learning techniques. ...
In the first part, we investigate the representation power of Texture Fields by analyzing how well the method can represent high frequency textures when trained on a single 3D object. ...
arXiv:1905.07259v1
fatcat:tsyq2cdhp5ghbgunry2fgocvfa
Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We then show how this freespace map can be used for real-time navigation on an indoor robot. ...
The results show that our system generalizes well, is suitable for real-time operation, and runs at around 55 fps on a small indoor robot powered by a low-power embedded GPU. ...
The following equation shows how the blur factor β is calculated, given that the function L(x, y) is a discrete convolution of the input image I(x, y) where x and y are image coordinates: L(x, y) = ...
arXiv:1902.00842v1
fatcat:hazqmamk7ze2dcnacrl37kxagy
A Deep Signed Directional Distance Function for Object Shape Representation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.11024v1 fatcat:yegi4y65kjem7msama5rqaopjy
Neural networks that map 3D coordinates to signed distance function (SDF) or occupancy values have enabled high-fidelity implicit representations of object shape. ...
This paper develops a new shape model that allows synthesizing novel distance views by optimizing a continuous signed directional distance function (SDDF). ...
For spheres with radii 0.4, 0.6, 10 the errors are 0.0076, 0.0268, 33.9721, respectively. First, we investigate how noise in the training data affects our method. ...
arXiv:2107.11024v2
fatcat:x2cbg4nenfc2nlgfo55qp6fo3y
3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Pointcloud registration methods working with unstructured pointclouds such as ICP are often computationally expensive or require a good initial guess. ...
With the advent of powerful, light-weight 3D LiDARs, they have become the hearth of many navigation and SLAM algorithms on various autonomous systems. ...
Therefore, we check how much the two pointclouds P and P overlap. ...
arXiv:2103.13808v2
fatcat:4izwxty2zvds3lct7scdu5usju
Supervised Learning of Labeled Pointcloud Differences via Cover-Tree Entropy Reduction
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
CDER applies to a training set of labeled pointclouds embedded in a common Euclidean space. ...
If typical pointclouds corresponding to distinct labels tend to differ at any scale in any sub-region, CDER can identify these differences in (typically) linear time, creating a set of distributional coordinates ...
The obvious questions are: how many Gaussians (modes) should be used, what are their means, and what are their covariances? ...
arXiv:1702.07959v3
fatcat:qdxf3ilmpfc2njtq5ozihs2biq
Shape Completion Enabled Robotic Grasping
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We explore how the quality of completions vary based on several factors. ...
Runtime shape completion is very rapid because most of the computational costs of shape completion are borne during offline training. ...
Each of the 32 examples in a batch was randomly sampled from the full training set with replacement. ...
arXiv:1609.08546v2
fatcat:bumbjkkkczgufchjhrsn77whgm
Linking Advanced Visualization and MATLAB for the Analysis of 3D Gene Expression Data
[chapter]
2012
Mathematics and Visualization
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
To maximize the impact of novel, complex data sets, such as PointClouds, the data needs to be accessible to biologists and comprehensible to developers of analysis functions. ...
Three-dimensional gene expression PointCloud data generated by the Berkeley Drosophila Transcription Network Project (BDTNP) provides quantitative information about the spatial and temporal expression ...
In addition, PCX provides a convenient GUI for the Matlab functions and parses PointCloud data, i.e., a developer does not need to know how to read PointCloud data. ...
doi:10.1007/978-3-642-21608-4_15
fatcat:5bymcaxqgnb3lht6fdne3s5coa
Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
While these approaches can relieve the computation burden to some extent, they are still limited in their processing capability for multiple scans. ...
Dense pointcloud data require a computationally expensive feature encoding process before semantic segmentation. ...
Intricate details initially present in the dense pointcloud input are removed during the downsampling process. This is undesirable since sparse pointclouds contain less geometric features. ...
arXiv:2009.08924v1
fatcat:6sczmd7lzvd3rjh6eevjvlhoza
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2007.11432v1 fatcat:oyuvxshk4reavgr4o4hpurbqku
Implicit functions represented as deep learning approximations are powerful for reconstructing 3D surfaces. ...
Nevertheless, such features are essential in building flexible models for both computer graphics and computer vision. ...
Implicit functions represented as deep learning approxima-
tions are powerful for reconstructing 3D surfaces. ...
arXiv:2007.11432v2
fatcat:mtcxrvdszjc4fhfo7gztc74gqq
AccSS3D: Accelerator for Spatially Sparse 3D DNNs
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
spatially-sparse 3D scene understanding, AccSS3D includes novel spatial locality-aware metadata structures, a near-zero latency and spatial sparsity-aware dataflow optimizer, a surface orientation aware pointcloud ...
Thus, we correlate SA Avg over randomly picked pointclouds ( Figure 15 ) and observe that: 1. ...
These components are majorly dominant for the initial and last few layers, where the voxel resolution sizes are higher. ...
arXiv:2011.12669v1
fatcat:vhtzlpqvh5ciri2mzmza3cjxqi
Addressing Overfitting on Pointcloud Classification using Atrous XCRF
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Advances in techniques for automated classification of pointcloud data introduce great opportunities for many new and existing applications. ...
Using a GAN training style, we can set up both of the A-XCRF loss functions as the same minimax objective function and perform parameter update using the gradient flow and parameter update in the GAN architecture ...
Such advantages are important for realtime classification of pointcloud data. ...
arXiv:1902.03088v1
fatcat:nboohiqz7fgltkbpzy4rd4g36m
Learning Risk-aware Costmaps for Traversability in Challenging Environments
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Because we are motivated by preserving the life of the robot, we tackle this learning problem from the perspective of learning tail-risks, i.e. the Conditional Value-at-Risk (CVaR). ...
., a probability distribution p(m|x 0:k , z 0:k ) over a possible set M, where z 0:k are sensor observations. ...
x, α)) outputs, which are fed into the loss function (Equation 13 ). ...
arXiv:2107.11722v1
fatcat:lvkbj53vxfcq5bo23zv3vtl6ki
Geometric Affordance Perception: Leveraging Deep 3D Saliency With the Interaction Tensor
2020
Frontiers in Neurorobotics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our approach works with visually perceived 3D pointclouds and enables to query a 3D scene for locations that support affordances such as sitting or riding, as well as interactions for everyday objects ...
Specific details on how we train such network are described in the Results and Evaluation section (section 5). ...
Besides, the manually annotated datasets used for training build on the assumption that objects in the environment have a pre-defined set of affordances; making uncertain how an agent would discover new ...
doi:10.3389/fnbot.2020.00045
pmid:32733228
pmcid:PMC7359196
fatcat:gwezipcvgnhuhgm6lpeiq3r5zi
« Previous
Showing results 1 — 15 out of 323 results