Mukund Varma T

Email: mukundvarmat at gmail dot com
Google Scholar | Twitter | GitHub

Hi 👋! I'm an incoming Ph.D. student at UC San Diego, jointly advised by Prof. Ravi Ramamoorthi and Prof. Hao Su. I received my bachelors degree from IIT Madras.


One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
Minghua Liu*Chao Xu*Haian Jin*Linghao Chen*Mukund Varma TZexiang XuHao Su
Under Review. 
[webpage]  [paper]  [code]  [demo]  [bib] 

U2NeRF: Unifying Unsupervised Underwater Image Restoration and Neural Radiance Fields
Manoj S*Mukund Varma T*Vinayak Gupta*Kaushik Mitra
Under Review. 

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts
Wenyan Cong*Hanxue Liang*Peihao WangZhiwen FanTianlong ChenMukund Varma TYi WangZhangyang Wang
ICCV 2023. 
[paper]  [code]  [bib] 

DeepSIFT: Rethinking Domain Generalization using Invariant Representations
Amil V DravidK Vikas MahendarYunhao GeHarkirat BehlMukund Varma TYogesh S RawatAggelos KatsaggelosNeel JoshiVibhav Vineet
Under Review. 

Is Attention All That NeRF Needs?
Mukund Varma T*Peihao Wang*Xuxi ChenTianlong ChenSubhashini VenugopalanZhangyang Wang
ICLR 2023. 
[webpage]  [paper]  [code]  [bib] 

Sparse Lottery Tickets are Data Efficient Image Recognizers
Mukund Varma TXuxi ChenZhenyu ZhangTianlong ChenSubhashini VenugopalanZhangyang Wang
NeurIPS 2022 (Spotlight). 
[paper]  [code]  [bib] 

NL Augmenter: A Collaborative Effort to Transform and Filter Text Datasets
Kaustubh DholeVarun GangalSebastian GehrmannAadesh GuptaZhenhao LiSaad MahmoodSimon MilleJascha Sohl-DicksteinAshish ShrivastavaSamson TanTongshuang (Sherry) WuAbinaya MahendiranMukund Varma TTanay Dixit,  et al.
NEJLT 2023 (GEM Workshop, IJCNLP 2021). 
[paper]  [code]  [bib] 

BIG Bench: Beyond the Imitation Game Benchmark
Jascha Sohl-DicksteinGuy Gur-AriEthan S DyerDaniel FreemanNoah FiedelJaehoon LeeRosanne LiuAitor LewkowyczVedant MisraAmbrose SloneMukund Varma TDiganta Misra,  et al.
TMLR 2023 (WELM Workshop, ICLR 2021). 
[paper]  [code]  [bib] 

ShapeFormer: A Transformer for Point Cloud Completion
Kushan Raj*Mukund Varma T*Dimple A ShajahanRamanathan Muthuganapathy
Under Review. 

[Re] On the Relationship between Self-Attention and Convolutional Layers
Mukund Varma T*Nishanth Prabhu*
ReScience-C (MLRC, NeurIPS 2020). 
[paper]  [code]  [bib] 

Point Transformer for Shape Classification and Retrieval of Urban Roof Point Clouds
Dimple A Shajahan*Mukund Varma T*Ramanathan Muthuganapathy
IEEE-GRSL 2021. 
[paper]  [code]  [bib]

Academic Service

  • Conference Reviewer:
    NeurIPS (2022, 2023), ICLR (2023), ICCV (2023).
  • Journal Reviewer:
    Computers and Graphics (2021, 2022).
  • Teaching Assistant (IIT Madras):
    • CS6700 Reinforcement Learning, Spring 2023.
    • EE5180 Introduction to Machine Learning, Spring 2023.
    • EE5179 Deep Learning for Imaging, Fall 2022.

About Me

I am an incoming Ph.D. student in the Department of Computer Science and Engineering at the University of California San Diego, where I will be co-advised by Prof. Ravi Ramamoorthi and Prof. Hao Su. My current research interests lie at the intersection of computer vision, computer graphics and machine learning, specifically to facilitate high quality 3D reconstructions and semantic understanding from multiple view points. I am lucky to be supported by the Jacobs School of Engineering Fellowship, and the SHORE Fellowship.

Before that, I graduated from IIT Madras, where I completed my (joint) bachelors and masters degree, advised by Prof. Balaraman Ravindran. At IIT Madras, I was also associated with the Advanced Geometric Computing Lab (hosts: Prof. M Ramanathan, Prof. Dimple Shajahan), and the Computational Imaging Lab (host: Prof. Kaushik Mitra). During my undergraduate, I was very fortunate to have spent time at the Visual Informatics Group at UT Austin (hosts: Prof. Zhangyang (Atlas) Wang, (now Prof. 🎉) Tianlong Chen), Google Research (hosts: Subhashini Venugopalan, Shanqing Cai, Varun Gulshan), Adobe Research (hosts: Mayur Hemani, Mausoom Sarkar, Balaji K), and Nvidia (host: Pallab Maji).

I am always happy to discuss / collaborate on related areas. Feel free to reach out to me via email.

Template adapted from Yinbo Chen