Search Results for author: Brojeshwar Bhowmick

Found 27 papers, 0 papers with code

Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture

no code implementations ECCV 2020 Dipanjan Das, Sandika Biswas, Sanjana Sinha, Brojeshwar Bhowmick

Current state-of-the-art methods fail to generate realistic animation from any speech on unknown faces due to their poor gen-eralization over different facial characteristics, languages, and accents.

Meta-Learning

Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos

no code implementations20 Nov 2023 Sushovan Chanda, Amogh Tiwari, Lokender Tiwari, Brojeshwar Bhowmick, Avinash Sharma, Hrishav Barua

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability of annotated data.

Motion Estimation

Exploring Social Motion Latent Space and Human Awareness for Effective Robot Navigation in Crowded Environments

no code implementations11 Oct 2023 Junaid Ahmed Ansari, Satyajit Tourani, Gourav Kumar, Brojeshwar Bhowmick

This work proposes a novel approach to social robot navigation by learning to generate robot controls from a social motion latent space.

Social Navigation

Sequence-Agnostic Multi-Object Navigation

no code implementations10 May 2023 Nandiraju Gireesh, Ayush Agrawal, Ahana Datta, Snehasis Banerjee, Mohan Sridharan, Brojeshwar Bhowmick, Madhava Krishna

The Multi-Object Navigation (MultiON) task requires a robot to localize an instance (each) of multiple object classes.

Object

Object Goal Navigation Based on Semantics and RGB Ego View

no code implementations20 Oct 2022 Snehasis Banerjee, Brojeshwar Bhowmick, Ruddra dev Roychoudhury

This paper presents an architecture and methodology to empower a service robot to navigate an indoor environment with semantic decision making, given RGB ego view.

Decision Making Navigate

Object Goal Navigation using Data Regularized Q-Learning

no code implementations27 Aug 2022 Nandiraju Gireesh, D. A. Sasi Kiran, Snehasis Banerjee, Mohan Sridharan, Brojeshwar Bhowmick, Madhava Krishna

Our framework incrementally builds a semantic map of the environment over time, and then repeatedly selects a long-term goal ('where to go') based on the semantic map to locate the target object instance.

Data Augmentation Navigate +2

Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation

no code implementations27 Aug 2022 D. A. Sasi Kiran, Kritika Anand, Chaitanya Kharyal, Gulshan Kumar, Nandiraju Gireesh, Snehasis Banerjee, Ruddra dev Roychoudhury, Mohan Sridharan, Brojeshwar Bhowmick, Madhava Krishna

This paper describes a framework for the object-goal navigation task, which requires a robot to find and move to the closest instance of a target object class from a random starting position.

Bayesian Inference Object +2

DoRO: Disambiguation of referred object for embodied agents

no code implementations28 Jul 2022 Pradip Pramanick, Chayan Sarkar, Sayan Paul, Ruddra dev Roychoudhury, Brojeshwar Bhowmick

Given an area where the intended object is, DoRO finds all the instances of the object by aggregating observations from multiple views while exploring & scanning the area.

Natural Language Understanding Object

Emotion-Controllable Generalized Talking Face Generation

no code implementations2 May 2022 Sanjana Sinha, Sandika Biswas, Ravindra Yadav, Brojeshwar Bhowmick

We propose a graph convolutional neural network that uses speech content feature, along with an independent emotion input to generate emotion and speech-induced motion on facial geometry-aware landmark representation.

Optical Flow Estimation Talking Face Generation +1

Simple means Faster: Real-Time Human Motion Forecasting in Monocular First Person Videos on CPU

no code implementations10 Nov 2020 Junaid Ahmed Ansari, Brojeshwar Bhowmick

To the best of our knowledge, we are the first to accurately forecast trajectories at a very high prediction rate of 78 trajectories per second on CPU.

Motion Forecasting

A Novel RF-assisted-Strobe System for Unobtrusive Vibration Detection of Machine Parts

no code implementations30 May 2020 Dibyendu Roy, Arijit Sinharay, Brojeshwar Bhowmick, Raj Rakshit, Tapas Chakravarty, Arpan Pal

In this paper, we propose a novel non-contact vibration measurement system that is competent in estimating linear and/or rotational motions of machine parts.

Identity-Preserving Realistic Talking Face Generation

no code implementations25 May 2020 Sanjana Sinha, Sandika Biswas, Brojeshwar Bhowmick

The necessary attributes of having a realistic face animation are 1) audio-visual synchronization (2) identity preservation of the target individual (3) plausible mouth movements (4) presence of natural eye blinks.

Audio-Visual Synchronization Image Reconstruction +1

Variational Clustering: Leveraging Variational Autoencoders for Image Clustering

no code implementations10 May 2020 Vignesh Prasad, Dipanjan Das, Brojeshwar Bhowmick

Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately.

Clustering Image Clustering

MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and Bayesian Tracking

no code implementations10 May 2020 Puneet Gupta, Brojeshwar Bhowmick, Arpan Pal

We alleviate these issues by proposing a novel face video based HR monitoring method MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking.

Integrating Objects into Monocular SLAM: Line Based Category Specific Models

no code implementations12 May 2019 Nayan Joshi, Yogesh Sharma, Parv Parkhiya, Rishabh Khawad, K. Madhava Krishna, Brojeshwar Bhowmick

The proposed parameterization associates 3D category-specific CAD model and object under consideration using a dictionary based RANSAC method that uses object Viewpoints as prior and edges detected in the respective intensity image of the scene.

Robotics

Lifting 2d Human Pose to 3d : A Weakly Supervised Approach

no code implementations3 May 2019 Sandika Biswas, Sanjana Sinha, Kavya Gupta, Brojeshwar Bhowmick

Few approaches have utilized training images from both 3d and 2d pose datasets in a weakly-supervised manner for learning 3d poses in unconstrained settings.

3D Pose Estimation

Indoor dense depth map at drone hovering

no code implementations25 Apr 2019 Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick

Autonomous Micro Aerial Vehicles (MAVs) gained tremendous attention in recent years.

3D point cloud registration with shape constraint

no code implementations4 Feb 2019 Swapna Agarwal, Brojeshwar Bhowmick

The proposed algorithm is shown to perform better in the presence of big rotation, structured and unstructured outliers and missing data.

Change Detection Point Cloud Registration +1

Deep Representation Learning Characterized by Inter-class Separation for Image Clustering

no code implementations19 Jan 2019 Dipanjan Das, Ratul Ghosh, Brojeshwar Bhowmick

Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks.

Clustering Image Clustering +1

Edge SLAM: Edge Points Based Monocular Visual SLAM

no code implementations14 Jan 2019 Soumyadip Maity, Arindam Saha, Brojeshwar Bhowmick

Feature based visual SLAMs do not produce reliable camera and structure estimates due to insufficient features in a low-textured environment.

Optical Flow Estimation Point Tracking

Motion Blur removal via Coupled Autoencoder

no code implementations24 Dec 2018 Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar

In this work, we propose a new formulation that recasts deblurring as a transfer learning problem, it is solved using the proposed coupled autoencoder.

Deblurring Transfer Learning

Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences

no code implementations23 Dec 2018 Vignesh Prasad, Dipanjan Das, Brojeshwar Bhowmick

The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way.

Visual Odometry

Constructing Category-Specific Models for Monocular Object-SLAM

no code implementations26 Feb 2018 Parv Parkhiya, Rishabh Khawad, J. Krishna Murthy, Brojeshwar Bhowmick, K. Madhava Krishna

These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework.

Object Object SLAM +1

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