Search Results for author: Siddhartha Chaudhuri

Found 35 papers, 19 papers with code

Learning to Infer Generative Template Programs for Visual Concepts

no code implementations20 Mar 2024 R. Kenny Jones, Siddhartha Chaudhuri, Daniel Ritchie

We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings.

Explorable Mesh Deformation Subspaces from Unstructured Generative Models

no code implementations11 Oct 2023 Arman Maesumi, Paul Guerrero, Vladimir G. Kim, Matthew Fisher, Siddhartha Chaudhuri, Noam Aigerman, Daniel Ritchie

Deep generative models of 3D shapes often feature continuous latent spaces that can, in principle, be used to explore potential variations starting from a set of input shapes.

Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly

no code implementations CVPR 2023 Xianghao Xu, Paul Guerrero, Matthew Fisher, Siddhartha Chaudhuri, Daniel Ritchie

We instead propose to decompose shapes using a library of 3D parts provided by the user, giving full control over the choice of parts.

3D Shape Reconstruction Retrieval

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes

1 code implementation5 May 2022 Noam Aigerman, Kunal Gupta, Vladimir G. Kim, Siddhartha Chaudhuri, Jun Saito, Thibault Groueix

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art.

The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts

no code implementations1 Dec 2021 Kai Wang, Paul Guerrero, Vladimir Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie

We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning.

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

1 code implementation12 Nov 2021 Jan Bednarik, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua

The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible.

Surface Reconstruction

BuildingNet: Learning to Label 3D Buildings

1 code implementation ICCV 2021 Pratheba Selvaraju, Mohamed Nabail, Marios Loizou, Maria Maslioukova, Melinos Averkiou, Andreas Andreou, Siddhartha Chaudhuri, Evangelos Kalogerakis

We introduce BuildingNet: (a) a large-scale dataset of 3D building models whose exteriors are consistently labeled, (b) a graph neural network that labels building meshes by analyzing spatial and structural relations of their geometric primitives.

3D Building Mesh Labeling 3D Semantic Segmentation

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

1 code implementation ICCV 2021 Jan Bednarik, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua, Noam Aigerman

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes.

Surface Reconstruction

A Unified Batch Selection Policy for Active Metric Learning

no code implementations15 Feb 2021 Priyadarshini K, Siddhartha Chaudhuri, Vivek Borkar, Subhasis Chaudhuri

To avoid redundancy between triplets, our method collectively selects batches with maximum joint entropy, which simultaneously captures both informativeness and diversity.

Active Learning Informativeness +1

Joint Learning of 3D Shape Retrieval and Deformation

1 code implementation CVPR 2021 Mikaela Angelina Uy, Vladimir G. Kim, Minhyuk Sung, Noam Aigerman, Siddhartha Chaudhuri, Leonidas Guibas

In fact, we use the embedding space to guide the shape pairs used to train the deformation module, so that it invests its capacity in learning deformations between meaningful shape pairs.

3D Shape Retrieval Retrieval

COALESCE: Component Assembly by Learning to Synthesize Connections

no code implementations5 Aug 2020 Kangxue Yin, Zhiqin Chen, Siddhartha Chaudhuri, Matthew Fisher, Vladimir G. Kim, Hao Zhang

We introduce COALESCE, the first data-driven framework for component-based shape assembly which employs deep learning to synthesize part connections.

Batch Decorrelation for Active Metric Learning

1 code implementation20 May 2020 Priyadarshini K, Ritesh Goru, Siddhartha Chaudhuri, Subhasis Chaudhuri

We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object $x_i$ is more similar to object $x_j$ than to $x_k$.

Active Learning Informativeness +1

Neural Subdivision

2 code implementations4 May 2020 Hsueh-Ti Derek Liu, Vladimir G. Kim, Siddhartha Chaudhuri, Noam Aigerman, Alec Jacobson

During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying the fixed topological updates of Loop Subdivision, but predicting vertex positions using a neural network conditioned on the local geometry of a patch.

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

2 code implementations ECCV 2020 Gopal Sharma, Difan Liu, Subhransu Maji, Evangelos Kalogerakis, Siddhartha Chaudhuri, Radomír Měch

We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives.

Affinity Graph Supervision for Visual Recognition

no code implementations CVPR 2020 Chu Wang, Babak Samari, Vladimir G. Kim, Siddhartha Chaudhuri, Kaleem Siddiqi

Affinity graphs are widely used in deep architectures, including graph convolutional neural networks and attention networks.

Image Classification

Neural Cages for Detail-Preserving 3D Deformations

1 code implementation CVPR 2020 Wang Yifan, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Olga Sorkine-Hornung

The goal of our method is to warp a source shape to match the general structure of a target shape, while preserving the surface details of the source.

FAN: Focused Attention Networks

no code implementations27 May 2019 Chu Wang, Babak Samari, Vladimir Kim, Siddhartha Chaudhuri, Kaleem Siddiqi

Thus far the learning of attention weights has been driven solely by the minimization of task specific loss functions.

Document Classification Object Detection +2

PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets

1 code implementation8 May 2019 Priyadarshini Kumari, Siddhartha Chaudhuri, Subhasis Chaudhuri

In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals.

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

1 code implementation ICCV 2019 Zhiqin Chen, Kangxue Yin, Matthew Fisher, Siddhartha Chaudhuri, Hao Zhang

The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels.

One-Shot Learning Representation Learning

AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss

no code implementations CVPR 2020 Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Li Yi, Leonidas Guibas, Hao Zhang

While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into up to (a user-specified) K parts.

Instance Segmentation Segmentation +1

Learning Material-Aware Local Descriptors for 3D Shapes

no code implementations20 Oct 2018 Hubert Lin, Melinos Averkiou, Evangelos Kalogerakis, Balazs Kovacs, Siddhant Ranade, Vladimir G. Kim, Siddhartha Chaudhuri, Kavita Bala

Unfortunately, only a small fraction of shapes in 3D repositories are labeled with physical mate- rials, posing a challenge for learning methods.

Material Classification Retrieval

SCORES: Shape Composition with Recursive Substructure Priors

no code implementations14 Sep 2018 Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Renjiao Yi, Hao Zhang

The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss.

GRAINS: Generative Recursive Autoencoders for INdoor Scenes

no code implementations24 Jul 2018 Manyi Li, Akshay Gadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, Hao Zhang

We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently.

Graphics

A Deep Recurrent Framework for Cleaning Motion Capture Data

no code implementations9 Dec 2017 Utkarsh Mall, G. Roshan Lal, Siddhartha Chaudhuri, Parag Chaudhuri

We present a deep, bidirectional, recurrent framework for cleaning noisy and incomplete motion capture data.

Tags2Parts: Discovering Semantic Regions from Shape Tags

1 code implementation CVPR 2018 Sanjeev Muralikrishnan, Vladimir G. Kim, Siddhartha Chaudhuri

We test our method on segmentation benchmarks and show that even with weak supervision of whole shape tags, our method can infer meaningful semantic regions, without ever observing shape segmentations.

TAG

ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling

1 code implementation6 Aug 2017 Minhyuk Sung, Hao Su, Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas

The combinatorial nature of part arrangements poses another challenge, since the retrieval network is not a function: several complements can be appropriate for the same input.

Graphics I.3.5

Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks

no code implementations14 Jun 2017 Haibin Huang, Evangelos Kalogerakis, Siddhartha Chaudhuri, Duygu Ceylan, Vladimir G. Kim, Ersin Yumer

We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching.

Semantic Segmentation

GRASS: Generative Recursive Autoencoders for Shape Structures

no code implementations5 May 2017 Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, Leonidas Guibas

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.

3D Shape Segmentation with Projective Convolutional Networks

1 code implementation CVPR 2017 Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, Siddhartha Chaudhuri

Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes.

Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.