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
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, and are often linearly separable. We obtain surprising results that show that random set functions can often obtain close to or even better accuracy than fully trained models. We investigate factors that affect the representative power of such embeddings quantitatively and qualitatively.
arXiv:2003.05410v1
fatcat:ttfl35wahve3tcv2lxq4mk34my
Group-disentangled Representation Learning with Weakly-Supervised Regularization
[article]
2021
arXiv
pre-print
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representations for groups of factors with weak supervision. Existing techniques to address this challenge merely constrain the approximate posterior by averaging over observations of a shared group. As a result, observations with a common set of variations are encoded to distinct latent
arXiv:2110.12185v1
fatcat:ywcwv65qbrbk7b57mrzj27x2ui
more »
... resentations, reducing their capacity to disentangle and generalize to downstream tasks. In contrast to previous works, we propose GroupVAE, a simple yet effective Kullback-Leibler (KL) divergence-based regularization across shared latent representations to enforce consistent and disentangled representations. We conduct a thorough evaluation and demonstrate that our GroupVAE significantly improves group disentanglement. Further, we demonstrate that learning group-disentangled representations improve upon downstream tasks, including fair classification and 3D shape-related tasks such as reconstruction, classification, and transfer learning, and is competitive to supervised methods.
Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders
[article]
2020
arXiv
pre-print
The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks. There is a growing interest in the question of whether features learned on one environment will generalize across different environments. We demonstrate here that VAE latent variables often focus on some factors of variation at the expense of others - in this case we refer to the features as "imbalanced". Feature imbalance leads to poor
arXiv:2005.05496v1
fatcat:lhbhuqkt25ahbcp5d5ik2nh2wq
more »
... generalization when the latent variables are used in an environment where the presence of features changes. Similarly, latent variables trained with imbalanced features induce the VAE to generate less diverse (i.e. biased towards dominant features) samples. To address this, we propose a regularization scheme for VAEs, which we show substantially addresses the feature imbalance problem. We also introduce a simple metric to measure the balance of features in generated images.
CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
[article]
2021
arXiv
pre-print
We introduce CAPRI-Net, a neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Our network takes an input 3D shape that can be provided as a point cloud or voxel grids, and reconstructs it by a compact assembly of quadric surface primitives via constructive solid geometry (CSG) operations. The network is self-supervised with a reconstruction loss, leading to faithful 3D
arXiv:2104.05652v1
fatcat:onnbfb7ikrdtnpxlyvuaoeukcq
more »
... ns with sharp edges and plausible CSG trees, without any ground-truth shape assemblies. While the parametric nature of CAD models does make them more predictable locally, at the shape level, there is a great deal of structural and topological variations, which present a significant generalizability challenge to state-of-the-art neural models for 3D shapes. Our network addresses this challenge by adaptive training with respect to each test shape, with which we fine-tune the network that was pre-trained on a model collection. We evaluate our learning framework on both ShapeNet and ABC, the largest and most diverse CAD dataset to date, in terms of reconstruction quality, shape edges, compactness, and interpretability, to demonstrate superiority over current alternatives suitable for neural CAD reconstruction.
Detecting Fake Drugs using Blockchain
2021
International journal of recent technology and engineering
The existing supply chain for the pharmaceutical industry is obsolete and lacks clear visibility over the entire system. Moreover, the circulation of counterfeit drugs in the market has increased over the years. According to the WHO report, around 10.5% of the medicinal drugs in lower / middle income countries are fake and such drugs may pose serious threats to public health, sometimes leading to death. Keeping these threats in mind, in this paper, we propose a blockchainbased model to track
doi:10.35940/ijrte.a5744.0510121
fatcat:jcj3usc6fndbfpecy72czjurx4
more »
... movement of drugs from the industry to the patient and to minimize the chances of a drug being counterfeit. The reasons for using blockchain technology in our work include its immutability property and easy tracking of an entity in the blockchain. Through this proposed model, the manufacturer would be able to upload the details corresponding to a drug, after which it will be sent for approval to the Government. Thereafter, hospitals and pharmacies, based upon their requirements, can request the approved drugs. In the future, if a patient wants some medication, then he or she has to request it on the blockchain network. The request will be sent to the nearest hospital/pharmacy and thereafter, the patient can collect the medication. To implement this model, we have used Hyperledger fabric due to the presence of many autoimplemented features in it. Our implementation of the proposed blockchain based model highlights that the model can successfully detect any drug being counterfeit. This will be beneficial for the users getting affected with counterfeit drugs. Moreover, with the proposed model, we can also track the movement of the drug beginning from the manufacturer right up to the patient consuming that drug.
UV-Net: Learning from Boundary Representations
[article]
2021
arXiv
pre-print
We introduce UV-Net, a novel neural network architecture and representation designed to operate directly on Boundary representation (B-rep) data from 3D CAD models. The B-rep format is widely used in the design, simulation and manufacturing industries to enable sophisticated and precise CAD modeling operations. However, B-rep data presents some unique challenges when used with modern machine learning due to the complexity of the data structure and its support for both continuous non-Euclidean
arXiv:2006.10211v2
fatcat:vccqocfodvcihke2kk4lx6mvli
more »
... ometric entities and discrete topological entities. In this paper, we propose a unified representation for B-rep data that exploits the U and V parameter domain of curves and surfaces to model geometry, and an adjacency graph to explicitly model topology. This leads to a unique and efficient network architecture, UV-Net, that couples image and graph convolutional neural networks in a compute and memory-efficient manner. To aid in future research we present a synthetic labelled B-rep dataset, SolidLetters, derived from human designed fonts with variations in both geometry and topology. Finally we demonstrate that UV-Net can generalize to supervised and unsupervised tasks on five datasets, while outperforming alternate 3D shape representations such as point clouds, voxels, and meshes.
BRepNet: A topological message passing system for solid models
[article]
2021
arXiv
pre-print
Boundary representation (B-rep) models are the standard way 3D shapes are described in Computer-Aided Design (CAD) applications. They combine lightweight parametric curves and surfaces with topological information which connects the geometric entities to describe manifolds. In this paper we introduce BRepNet, a neural network architecture designed to operate directly on B-rep data structures, avoiding the need to approximate the model as meshes or point clouds. BRepNet defines convolutional
arXiv:2104.00706v2
fatcat:q2em4c5mafcjnal3d72wqugmru
more »
... els with respect to oriented coedges in the data structure. In the neighborhood of each coedge, a small collection of faces, edges and coedges can be identified and patterns in the feature vectors from these entities detected by specific learnable parameters. In addition, to encourage further deep learning research with B-reps, we publish the Fusion 360 Gallery segmentation dataset. A collection of over 35,000 B-rep models annotated with information about the modeling operations which created each face. We demonstrate that BRepNet can segment these models with higher accuracy than methods working on meshes, and point clouds.
Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning
[article]
2020
arXiv
pre-print
A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use datasets that are aligned, require objects to be reconstructed and suffer from deteriorated performance on downstream tasks. To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the
arXiv:2006.02598v2
fatcat:btxte6op5rhvrmqlqvi2lf2lle
more »
... utual information between 3D objects and their "chunks" to improve the representations in aligned datasets. Furthermore, we can achieve rotation invariance in SO(3) group by maximizing the mutual information between the 3D objects and their geometric transformed versions. Finally, we conduct several experiments such as clustering, transfer learning, shape retrieval, and achieve state of art results.
CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation
[article]
2022
arXiv
pre-print
Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at a large scale. We present a simple yet effective method for zero-shot text-to-shape generation that circumvents such data scarcity. Our proposed method, named CLIP-Forge, is based on a two-stage
arXiv:2110.02624v2
fatcat:zb4nyevqjjgzxd3cbiibxz3rwi
more »
... ing process, which only depends on an unlabelled shape dataset and a pre-trained image-text network such as CLIP. Our method has the benefits of avoiding expensive inference time optimization, as well as the ability to generate multiple shapes for a given text. We not only demonstrate promising zero-shot generalization of the CLIP-Forge model qualitatively and quantitatively, but also provide extensive comparative evaluations to better understand its behavior.
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
[article]
2022
arXiv
pre-print
Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our
arXiv:2111.12772v2
fatcat:w44jtwy2xbgltfzmxoc6k3jity
more »
... ts show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the Fusion 360 Gallery assembly dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.
UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps
[article]
2021
arXiv
pre-print
Boundary Representations (B-Reps) are the industry standard in 3D Computer Aided Design/Manufacturing (CAD/CAM) and industrial design due to their fidelity in representing stylistic details. However, they have been ignored in the 3D style research. Existing 3D style metrics typically operate on meshes or pointclouds, and fail to account for end-user subjectivity by adopting fixed definitions of style, either through crowd-sourcing for style labels or hand-crafted features. We propose
arXiv:2105.02961v3
fatcat:sxdznzourzddnbtvaz3g4yy2kq
more »
... , a style similarity measure for B-Reps that leverages the style signals in the second order statistics of the activations in a pre-trained (unsupervised) 3D encoder, and learns their relative importance to a subjective end-user through few-shot learning. Our approach differs from all existing data-driven 3D style methods since it may be used in completely unsupervised settings, which is desirable given the lack of publicly available labelled B-Rep datasets. More importantly, the few-shot learning accounts for the inherent subjectivity associated with style. We show quantitatively that our proposed method with B-Reps is able to capture stronger style signals than alternative methods on meshes and pointclouds despite its significantly greater computational efficiency. We also show it is able to generate meaningful style gradients with respect to the input shape, and that few-shot learning with as few as two positive examples selected by an end-user is sufficient to significantly improve the style measure. Finally, we demonstrate its efficacy on a large unlabeled public dataset of CAD models. Source code and data will be released in the future.
UNIST: Unpaired Neural Implicit Shape Translation Network
[article]
2021
We introduce UNIST, the first deep neural implicit model for general-purpose, unpaired shape-to-shape translation, in both 2D and 3D domains. Our model is built on autoencoding implicit fields, rather than point clouds which represents the state of the art. Furthermore, our translation network is trained to perform the task over a latent grid representation which combines the merits of both latent-space processing and position awareness, to not only enable drastic shape transforms but also well
doi:10.48550/arxiv.2112.05381
fatcat:6cinlgdwqbadhfubjlqhwefoay
more »
... preserve spatial features and fine local details for natural shape translations. With the same network architecture and only dictated by the input domain pairs, our model can learn both style-preserving content alteration and content-preserving style transfer. We demonstrate the generality and quality of the translation results, and compare them to well-known baselines.
INDIA Under the Banner of
International Journal of Physics and Mathematical Sciences'
unpublished
O-P 2 O 5 GLASSY IONIC SYSTEM IN Jamil Akhtar Soft magnetic nanocomposites thin films; R&D 10-13 THERMALLY UNSTABLE REGION initiatives at CEERI 10:45-11:45AM Munesh Rathore, Neha Gupta, Himanshu Tyagi, Aditya ...
CONCENTRATION OF 62-67 SOLUTION *Amar Singh and Navin Singh 15 ABSORBANCE AND FLUORESCENCE SPECTRAL ANALYSIS OF Pr 3+ IONS 68-73 DOPED BISMUTH BORO-SILICATE GLASSES * Sunil Bhardwaj, Rajni Shukla, Sujata Sanghi ...
fatcat:esujdtfzdnhcrnzdjbm3u4hnfu
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
[article]
2020
arXiv
pre-print
Acknowledgements We would like to thank Aditya Sanghi and Ara Danielyan for their useful input through the course of this research. ...
arXiv:2007.04525v1
fatcat:2amdw43p2nf2lou7iupu35w4o4
Text2Mesh: Text-Driven Neural Stylization for Meshes
[article]
2021
arXiv
pre-print
thousands of tiny mlps, 2021.
[32] Honghua Li, Hao Zhang, Yanzhen Wang, Junjie Cao, Ariel
[48] Aditya Sanghi, Hang Chu, Joseph G Lambourne ...
on computer vision and pattern recognition, pages 3907– [44] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya
3916, 2018. ...
arXiv:2112.03221v1
fatcat:2mfgjh37lna5hnjj6pvms6zuey
« Previous
Showing results 1 — 15 out of 24 results