Badrinath Singhal

I am a PhD student at the Indian Institute of Science (IISc), Bangalore, advised by Prof. Venkatesh Babu. My research focuses on making 3D vision models efficient and deployable across the full compute spectrum, from edge devices to the cloud, by enabling controllable compression of the underlying representation.

Bio: Previously, I worked at Axera Tech and EmbodyMe in Tokyo, Japan, as a Machine Learning Scientist, where I worked on various projects in generative models and camera ISP algorithms. I graduated with a BTech from IIT Guwahati, majoring in Electronics and Electrical Engineering with a minor in Computer Science, where I worked on CORDIC (Coordinate Rotation Digital Computer), a hardware-efficient iterative algorithm to calculate SVD of large matrices. I attended Kendriya Vidyalaya C.R.P.F. Amerigog for secondary school.

I enjoy sharing this talk by Richard Hamming on doing great research (the transcript is especially good). Also here is Neil Patrick Harris hosting Tony Awards 2013 that I like to watch. Outside of work, I try not to take things too seriously. I enjoy running, guitar, comedy, food, tea, sunrises/sunsets, and mathematics.

Feel free to reach out for discussions, collaborations, or coffee!

CV
Badrinath Singhal

News

Jun 2026 Paper AdaptiveSplat accepted at ECCV 2026.
Apr 2026 Presented my work at the EECS Research Symposium at IISc.
Dec 2025 Organised tutorial on Generative Models for Content Creation, Reconstruction, and Beyond at ICVGIP 2025.
Aug 2025 Grateful to receive the TCS Research Scholarship! (upto 40 awardees nationwide).
Aug 2025 Excited to be selected as a recipient of the Qualcomm Innovation Fellowship! (18 recipients nationwide)
Jan 2023 Started as Senior Machine Learning Engineer at Axera-Tech.
Mar 2020 Joined EmbodyMe as a Machine Learning Scientist.

Publications

AdaptiveSplat teaser
AdaptiveSplat: Texture-Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
Badrinath Singhal, Srihari K G, Sreehari Iyer, Ankit Dhiman, R. Venkatesh Babu
European Conference on Computer Vision (ECCV), 2026
Project Page 
@inproceedings{singhal2026adaptivesplat,
  title        = {AdaptiveSplat: Texture-Aware Controllable 3D Gaussian Allocation
                  for Feed-Forward Reconstruction},
  author       = {Singhal, Badrinath and K G, Srihari and Iyer, Sreehari
                  and Dhiman, Ankit and Babu, R. Venkatesh},
  booktitle    = {European Conference on Computer Vision (ECCV)},
  year         = {2026},
  organization = {Vision and AI Lab, Indian Institute of Science}
}
IJCNN paper
Spinal Stenosis Detection in MRI using Modular Coordinate Convolutional Attention Networks
Uddeshya Upadhyay, Badrinath Singhal, Meenakshi Singh
International Joint Conference on Neural Networks (IJCNN), 2019
Paper 
@InProceedings{IJCNN,
  author    = {Uddeshya Upadhyay and Badrinath Singhal and Meenakshi Singh},
  title     = {Spinal Stenosis Detection in MRI using Modular Coordinate
               Convolutional Attention Networks},
  booktitle = {International Joint Conference on Neural Networks (IJCNN)},
  year      = {2019},
}
FUZZ-IEEE paper
Performance Analysis of a Novel IT2 FCM Algorithm
Shashank Huddedar, Mayank Kagliwal, Badrinath Singhal, Frank Rhee
IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2018
Paper 
@InProceedings{FUZZ,
  author    = {Shashank Huddedar and Mayank Kagliwal
               and Badrinath Singhal and Frank Rhee},
  title     = {Performance Analysis of a Novel IT2 FCM Algorithm},
  booktitle = {IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)},
  year      = {2018},
}

Teaching

Teaching Assistant: DS265o: Deep Learning for Visual Analytics Indian Institute of Science
2026
Teaching Assistant: DS265: Deep Learning for Computer Vision Indian Institute of Science
2026
Teaching Assistant: DS265: Deep Learning for Computer Vision Indian Institute of Science
2025