Prajwal Kumar Singh

I am a Computer Science Ph.D. student at IIT Gandhinagar, India, advised by Prof. Shanmuganathan Raman. My research interests include 3D computer vision, generative networks, graph neural networks, representation learning and brain-computer interface (BCI).

Email  /  Google Scholar  /  GitHub  /  LinkedIn  /  Twitter  /  YoutTube  /  CV  /  Python Notes

Publications
Learning Robust Deep Visual Representations from EEG Brain Recordings
Prajwal Singh, Dwip Dalal, Gautam Vashishtha, Krishna Miyapuram, Shanmuganathan Raman,
WACV 2024 (featured in WACV Daily and Best of WACV 2024)
project page/ arXiv/ WACV Daily/ Best of WACV 2024

This study presents a two-stage method utilizing EEG-derived features for deep representation learning, demonstrating its generalizability across multiple datasets and achieving superior results in EEG-based image synthesis, including image reconstruction and classification tasks, outperforming existing GAN-based methods.

Hand Shadow Art: A Differentiable Rendering Perspective
Aalok Gangopadhyay, Prajwal Singh, Ashish Tiwari, Shanmuganathan Raman,
Pacific Graphics: Poster, 2023 (Best Poster Award)
project page/ arXiv/ PG2023

This work introduces a novel approach using differentiable rendering to deform hand models, enabling the creation of meaningful and consistent shadows resembling desired target images.

TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network
Prajwal Singh, Ashish Tiwari, Kaustubh Sadekar, Shanmuganathan Raman,
Pacific Graphics: Poster, 2023
project page/ arXiv/ PG2023

This work proposes a tree-structured autoencoder framework to generate robust embeddings of point clouds by utilizing hierarchical information using graph convolution. We perform multiple experiments to assess the quality of embeddings generated by the proposed encoder architecture and visualize the t-SNE map to highlight its ability to distinguish between different object classes.

Single Image LDR to HDR Conversion using Conditional Diffusion
Dwip Dalal, Gautam Vashishtha, Prajwal Singh, Shanmuganathan Raman
ICIP, 2023
project page/ arXiv/ video

We formulate the problem as an image-to-image (I2I) translation task and propose a conditional Denoising Diffusion Probabilistic Model (DDPM) based framework using classifier-free guidance. We incorporate a deep CNN-based autoencoder in our proposed framework to enhance the quality of the latent representation of the input LDR image used for conditioning.

EEG2IMAGE: Image Reconstruction from EEG Brain Signals
Prajwal Singh, Pankaj Pandey, Krishna Miyapuram, Shanmuganathan Raman
ICASSP, 2023
project page/ arXiv/ video

We use a contrastive learning method in the proposed framework to extract features from EEG signals and synthesize the images from extracted features using conditional GAN. We modify the loss function to train the GAN, which enables it to synthesize 128x128 images using a small number of images.

APEX-Net: Automatic Plot Extraction Network
Aalok Gangopadhyay, Prajwal Singh, Shanmuganathan Raman
NCC, 2022
project page/ arXiv/ video

To minimize this intervention, we propose APEX-Net, a deep learning based framework with novel loss functions for solving the plot extraction problem. We introduce APEX-1M, a new large scale dataset which contains both the plot images and the raw data.

LS-HDIB: A Large Scale Handwritten Document Image Binarization Dataset
Kaustubh Sadekar, Ashish Tiwari, Prajwal Singh, Shanmuganathan Raman
ICPR, 2022
project page/ arXiv/ video

We propose a large scale dataset of 1 Million challenging images for the task of hand written document image binarisation (HDIB) with accurate segmentation groundtruth.

DILIE: deep internal learning for image enhancement
Indradeep Mastan, Shanmuganathan Raman, Prajwal Singh
WACV VAQ Workshop, 2022
project page/ arXiv/ video

We perform image enhancement using a deep internal learning framework. Our Deep Internal Learning for Image Enhancement framework (DILIE) enhances content features and style features and preserves semantics in the enhanced image.


Thanks to Jon Barron for this awesome template and Pratul Srinivasan for additional formatting.
Last updated July 2023.