Research(superscript * indicates equal contribution)
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. Some papers are highlighted.
|
|
GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views
Vinayak Gupta*,
Girish Rongali*,
Mukund Varma T*,
Kaushik Mitra
under review.
A generalizable framework for novel view synthesis using degraded input captures containing any imperfection type.
|
|
A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose
Kaiwen Jiang,
Yang Fu,
Mukund Varma T,
Yash Belhe,
Xiaolong Wang,
Hao Su,
Ravi Ramamoorthi
SIGGRAPH 2024.
project /
pdf /
code /
bib
A camera-free novel view synthesis technique from sparse input views (as few as 3 images of large-scale scenes).
|
|
Lift3D: Zero Shot Lifting of Any 2D Vision Model to 3D
Mukund Varma T,
Peihao Wang,
Zhiwen Fan,
Zhangyang Wang,
Hao Su,
Ravi Ramamoorthi
CVPR 2024.
project /
pdf /
code /
bib
General framework to lift any pretrained 2D vision model to generate 3D consistent outputs with no additional optimization.
|
|
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 T,
Zexiang Xu,
Hao Su
NeurIPS 2023.
project /
pdf /
code /
demo /
bib
Improves consistency of off-the-shelf multi-view generation techniques using a generalizable SDF, enabling super fast 3D generation from a single image.
|
|
U2NeRF: Unifying Unsupervised Underwater Image Restoration and Neural Radiance Fields
Manoj S*,
Mukund Varma T*,
Vinayak Gupta*,
Kaushik Mitra
ICLR Tiny Papers 2024.
pdf /
code /
bib
A unsupervised learning pipeline for generalizable novel view synthesis and restoration of underwater scenes by disentangling into individual image formation components.
|
|
Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts
Wenyan Cong*,
Hanxue Liang*,
Peihao Wang,
Zhiwen Fan,
Tianlong Chen,
Mukund Varma T,
Yi Wang,
Zhangyang Wang
ICCV 2023.
pdf /
code /
bib
We scale up generalizable NeRF training by borrowing the concept of mixture of experts from language models.
|
|
DeepSIFT: Rethinking Domain Generalization using Invariant Representations
Amil V Dravid,
K Vikas Mahendar,
Yunhao Ge,
Harkirat Behl,
Mukund Varma T,
Yogesh S Rawat,
Aggelos Katsaggelos,
Neel Joshi,
Vibhav Vineet
under review.
We present emperical evidence that convolutional networks trained on sift features improve robustness to unseen out-of-domain data with minimal to no-loss in in-domain performance.
|
|
Is Attention All That NeRF Needs?
Mukund Varma T*,
Peihao Wang*,
Xuxi Chen,
Tianlong Chen,
Subhashini Venugopalan,
Zhangyang Wang
ICLR 2023.
project /
pdf /
code /
bib
We propose a generalizable neural scene representation and rendering pipeline that achieves superior quality compared to previous methods.
|
|
Sparse Lottery Tickets are Data Efficient Image Recognizers
Mukund Varma T,
Xuxi Chen,
Zhenyu Zhang,
Tianlong Chen,
Subhashini Venugopalan,
Zhangyang Wang
NeurIPS 2022 (Spotlight).
pdf /
code /
bib
Sparse networks identified using iterative magnitude pruning showcase improved data-efficiency and robustness compared to their dense counterparts.
|
|
NL Augmenter: A Collaborative Effort to Transform and Filter Text Datasets
Kaustubh Dhole,
Varun Gangal, ...
Mukund Varma T,
Tanay Dixit,
et al.
NEJLT 2023 (GEM Workshop, IJCNLP 2021).
pdf /
code /
bib
Collaborative repository of natural language transformations.
|
|
BIG Bench: Beyond the Imitation Game Benchmark
Jascha Sohl-Dickstein,
Guy Gur-Ari, ...
Mukund Varma T,
Diganta Misra,
et al.
TMLR 2023 (WELM Workshop, ICLR 2021).
pdf /
code /
bib
Collaborative benchmark for measuring and extrapolating the capabilities of language models.
|
|
ShapeFormer: A Transformer for Point Cloud Completion
Kushan Raj*,
Mukund Varma T*,
Dimple A Shajahan,
Ramanathan Muthuganapathy
under review.
A specialized pipeline for point cloud shape completion that can generalize to synthetic and real partial scans from seen and unseen categorical types.
|
|
[Re] On the Relationship between Self-Attention and Convolutional Layers
Mukund Varma T*,
Nishanth Prabhu*
ReScience-C (MLRC, NeurIPS 2020).
pdf /
code /
bib
We introduce Hierarchical Attention, a reccurent transformer module that immitates convolution-like operation with significantly lower computational budget.
|
|
Point Transformer for Shape Classification and Retrieval of Urban Roof Point Clouds
Dimple A Shajahan*,
Mukund Varma T*,
Ramanathan Muthuganapathy
IEEE-GRSL 2021.
pdf /
code /
bib
We propose a transformer architecture for sparse set learning, e.g. point cloud understanding.
|
Academic Service
-
Conference Reviewer:
NeurIPS (2022, 23, 24), ICLR (2023, 24), ICCV (2023), ECCV (2024), CVPR (2024).
-
Journal Reviewer:
Computers and Graphics (2021, 22).
-
Teaching Assistant (IIT Madras):
- CS6700 Reinforcement Learning, Spring 2023.
- EE5180 Introduction to Machine Learning, Spring 2023.
- EE5179 Deep Learning for Imaging, Fall 2022.
|
Misc
I enjoy hiking ⛰️ (cuz duh I am a boring computer science kid), used to sketch ✏️ a bit, and love playing most sports, particularly badminton 🏸, tennis 🎾 and soccer ⚽ (ahem I am american XD).
Feel free to reach out to chat about anything, but headsup I love to yap (it can be scary, umm I am kidding lmao).
Fun fact: my name in chinese 牧坤 (Mù kūn) when broken down essentially means "to manage" 牧 (Mù) and 坤 (kūn), one of the eight trigrams in I Ching that represents "the earth" 😤.
|
Template stolen from here.
|
|