Search Results for author: Pulak Purkait

Found 14 papers, 3 papers with code

NeuRoRA: Neural Robust Rotation Averaging

1 code implementation ECCV 2020 Pulak Purkait, Tat-Jun Chin, Ian Reid

Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.

Fine-tuning Robot Navigation +1

SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes

no code implementations ECCV 2020 Pulak Purkait, Christopher Zach, Ian Reid

Our method learns the co-occurrences, and appearance parameters such as shape and pose, for different objects categories through a grammar-based auto-encoder, resulting in a compact and accurate representation for scene layouts.

Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions

no code implementations7 Jun 2019 Pulak Purkait, Christopher Zach, Ian Reid

In our experiments we demonstrate that a CNN trained by minimizing the proposed loss is able to predict semantic categories for visible and occluded object parts without requiring to increase the network size (compared to a standard segmentation task).

Semantic Segmentation

Morphological Networks for Image De-raining

1 code implementation8 Jan 2019 Ranjan Mondal, Pulak Purkait, Sanchayan Santra, Bhabatosh Chanda

Mathematical morphological methods have successfully been applied to filter out (emphasize or remove) different structures of an image.

SSIM

Weakly supervised learning of indoor geometry by dual warping

1 code implementation10 Aug 2018 Pulak Purkait, Ujwal Bonde, Christopher Zach

A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose.

Maximum Consensus Parameter Estimation by Reweighted $\ell_1$ Methods

no code implementations22 Mar 2018 Pulak Purkait, Christopher Zach, Anders Eriksson

Robust parameter estimation in computer vision is frequently accomplished by solving the maximum consensus (MaxCon) problem.

Learning monocular visual odometry with dense 3D mapping from dense 3D flow

no code implementations6 Mar 2018 Cheng Zhao, Li Sun, Pulak Purkait, Tom Duckett, Rustam Stolkin

Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then used by a 3D flow associated layer in the L-VO network to generate dense 3D flow.

Monocular Visual Odometry

SPP-Net: Deep Absolute Pose Regression with Synthetic Views

no code implementations9 Dec 2017 Pulak Purkait, Cheng Zhao, Christopher Zach

In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image.

Image-Based Localization Pose Estimation

Minimal Solvers for Monocular Rolling Shutter Compensation under Ackermann Motion

no code implementations8 Dec 2017 Pulak Purkait, Christopher Zach

Modern automotive vehicles are often equipped with a budget commercial rolling shutter camera.

Motion Compensation

Rolling Shutter Correction in Manhattan World

no code implementations ICCV 2017 Pulak Purkait, Christopher Zach, Ales Leonardis

A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image.

Dense RGB-D semantic mapping with Pixel-Voxel neural network

no code implementations30 Sep 2017 Cheng Zhao, Li Sun, Pulak Purkait, Rustam Stolkin

For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously understand the higher level meaning of the scene contexts.

3D Reconstruction Scene Understanding +1

Clustering with Hypergraphs: The Case for Large Hyperedges

no code implementations IEEE Transactions on Pattern Analysis and Machine Intelligence 2016 Pulak Purkait, Tat-Jun Chin, Hanno Ackermann, David Suter

The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision.

Face Clustering Motion Segmentation

Efficient Globally Optimal Consensus Maximisation With Tree Search

no code implementations CVPR 2015 Tat-Jun Chin, Pulak Purkait, Anders Eriksson, David Suter

We aim to change this state of affairs by proposing a very efficient algorithm for global maximisation of consensus.

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