Yash Kumar Sahu

I am a research associate at the I3D Lab, Indian Institute of Science (IISc) advised by Prof. Pradipta Biswas.

Previously, I was a full-time research student at the GCDSL-MRL lab at IISc, developing 3D path planning algorithms for drones under the supervision of Prof. Debasish Ghose. I completed my bachelors and masters in Computer Science from Indian Institute of Information Technology, Design and Manufacturing (IIITDM), Kancheepuram, with a thesis titled "Synthetic Data Generation Using GANs and Diffusion Models for Low Resource Domains" advised by Prof. Pradipta Biswas and co-advised by Prof. Sadagopan N.

 yashkumars [at] iisc.ac.in    /   CV   /   Linkedin   /   Github   /   Google Scholar   

Blind Tactile Exploration for Surface Reconstruction
Yashaswi Sinha*, Soumojit Bhattacharya*,  Yash Kumar Sahu, Pradipta Biswas
ICRA 2025

[ paper (coming soon) ]

Exploring and 3D reconstructing complex shapes using only tactile feedback from a single touch, without relying on vision.

Diffuse Your Data Blues: Augmenting Low-Resource Datasets via User-Assisted Diffusion
Yashaswi Sinha, Yash Kumar Sahu*, Shravan Shanmugam*, Abhishek Mukhopadhyay, Pradipta Biswas
IUI 2025

[ paper ]

Enabling the user to customize backgrounds and foregrounds in diffusion-based image generation, supporting tasks like image data augmentation to enhance object detection accuracy.

A Comparative Study on Image Translation GAN Models to Improve Object Detection Accuracy on Low-Resource Domains
Yash Kumar Sahu, Abhishek Mukhopadhyay, Gyanig Kumar, Pradipta Biswas
ICTTVS 2024

[ paper ]

Improving object detection in scenarios with limited number of images by augmenting that dataset with GAN generated synthetic images.

Vision-Based Object Sorting in Dynamic Environments using YOLO for RoboCup ARM Challenge 2023
Yash Kumar Sahu, Radhika Mittal, Deep Patel, Chayan Maiti, M Sreekumar
CICT 2023

[ paper ]

Performing autonomous robotic manipulation for sorting objects in constantly changing environments.

Comparing Computer Vision Models for Low Resource Dataset to Develop a Mixed Reality based Manual Assembly Assistant
Subin Raj, Gyanig Kumar, Yash Kumar Sahu, Pradipta Biswas

[ paper (coming soon) ]

Proposing AR and AI assistance for complex object assembly, showing YOLOv8 with real and synthetic data improves accuracy, and MR systems accelerate tasks over traditional methods.

Indian Institute of Information Technology, Design and Manufacturing (IIITDM), Kancheepuram
B.Tech & M.Tech in Computer Science
Aug 2019 - July 2024