Snehal Singh Tomar

stomar@cs.stonybrook.edu

Hello! I am a first year CS Ph.D. student at Stony Brook University. My research aims to build Interpretable Deep Generative Models for Computer Vision applications. I enjoy working on problems in Computational Photography and 3D Computer Vision as well. Aside from that, I serve as an AI evangelist at SolveitNOW, a startup that is revolutionizing peer learning for K-12 students. Previously, I was a pre-doctoral fellow with the Visual and Embodied AI group at TCS Research, working on efficient 3D mesh animation using Self-Supervised Graph Neural Networks. Before that, I graduated from the Indian Institute of Technology Madras with an MS (by Research) in Electrical Engineering, having received the Institute Research Award for excellence in research. There, I was a part of the Image Processing and Computer Vision (IPCV) Lab, advised by Prof. A.N. Rajagopalan.

While I was an undergrad, I did several research internships with Prof. Shubhendu Bhasin at IIT Delhi, working in the domain of Control Systems and Robotics. I was also a part of my university’s AI Robotics Team, where we worked on building an autonomous car.

News

02.2024	PNeRV has been accpeted to the Transactions on Machine Learning Research (TMLR)!
01.2024	I started my Ph.D. in CS @ Stony Brook!
12.2023	Latents2Semantics has been accepted at AAAI-2024: AI for Digital Human Workshop as an oral paper! I have also been selected for the AAAI-24 Travel Scholarship!
11.2023	I will be serving as a reviewer for CVPR 2024!
06.2023	I am excited to be starting at TCS Research as a Pre-doctoral fellow!
11.2022	I have been awarded the IIT Madras Institute Research Award for excellence in research! I am honored to be selected among the top 3 out of the 746 MS students at IITM, based on research.
06.2022	I am presenting at CV4ARVR and attending CVPR 2022 in-person from June 19 to June 24, 2022! Many thanks to the IITM Institute Travel Grant for making this possible!

Peer-Reviewed Publications

PNeRV: A Polynomial Neural Representation for Videos

S. Gupta, Snehal Singh Tomar, Grigorios Chrysos , S. Das, and A.N. Rajagopalan

Transactions on Machine Learning Research (TMLR) 2024

Paper

Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images (Oral)

Snehal Singh Tomar, and A.N. Rajagopalan

38 ^th AAAI Conference on Artificial Intelligence 2024 - Workshop on AI for Digital Human

Bib arXiv

@article{tomarAAAI2024,
  				title = {Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images},
  				author = {Tomar, Snehal Singh,and Rajagopalan, A.N.},
			  	journal = {AAAI-24 Workshop on AI for Digital Human},
			  	year = {2024},
}

Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images (Student Abstract)

Snehal Singh Tomar, Maitreya Suin , and A.N. Rajagopalan

37 ^th AAAI Conference on Artificial Intelligence 2023

Bib arXiv AAAI-23 Proceedings

@article{tomarAAAI2023,
  				title = {Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images (Student Abstract)},
  				author = {Tomar, Snehal Singh, Suin, Maitreya, and Rajagopalan, A.N.},
			  	journal = {AAAI Conference on Artificial Intelligence, 37},
			  	year = {2023},
}

Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation (Oral)

Snehal Singh Tomar, Maitreya Suin , and A.N. Rajagopalan

ECCV Workshop on Advances in Image Manipulation (AIM), Tel-Aviv 2022

Bib arXiv ECCV-22 Proceedings Video Code

@article{tomarEccvw2022,
  				title = {Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation},
  				author = {Tomar, Snehal Singh, Suin, Maitreya, and Rajagopalan, A.N.},
			  	journal = {ECCV Workshop on Advances in Image Manipulation (AIM), Tel-Aviv},
			  	year = {2022},
}

Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images

Snehal Singh Tomar and A.N. Rajagopalan

CVPR Workshop on Computer Vision for Augmented and Virtual Reality, New Orleans, LA 2022

Bib arXiv CVPRW Proceedings video Code

@article{tomarCvprw2022,
  				title = {Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images},
  				author = {Tomar, Snehal Singh and Rajagopalan, A.N.},
			  	journal = {CVPR Workshop on Computer Vision for Augmented and Virtual Reality, New Orleans, LA},
			  	year = {2022},
}

Python-Based Fuzzy Classifier for Cashew Kernels (Best Paper Award)

Tomar, Snehal Singh, and Narendra, V. G.

Soft Computing for Problem Solving. Advances in Intelligent Systems and Computing, vol 816. Springer, Singapore 2019

Bib Paper (Springer Link)

@article{10.1007/978-981-13-1592-3_28,
  				title = {Python-Based Fuzzy Classifier for Cashew Kernels},
  				author = {Tomar, S.S., Narendra, V.G.},
			  	journal = {Bansal, J., Das, K., Nagar, A., Deep, K., Ojha, A. (eds) Soft Computing for Problem Solving. Advances in Intelligent Systems and Computing, vol 816. Springer, Singapore},
			  	year = {2019},
}