Priyanka Mandikal
I am a PhD student in Computer Science at UT Austin working with Prof. Kristen Grauman. I was a visiting researcher at Facebook AI Research from 2021-23. My interest lies at the intersection of computer vision, machine learning and robotics.
In my PhD, I work on learning object-centric representations for robotic manipulation. Through the study of artificial intelligence, I hope to form a better understanding of the very nature of human intelligence and existence.
Prior to joining grad school, I worked with Prof. Venkatesh Babu as a research assistant at the Indian Institute of Science (IISc) on a wide range of vision problems including 3D model reconstruction, computational photography, and 3D human motion models.
I also spent a couple of months during Summer 2019 as a visiting researcher with Prof. Michael Black at the Max Planck Institute for Intelligent Systems in Tuebingen, Germany.
Previously, I graduated from BITS Pilani, India with a double major in Computer Science and Physics in 2017. During my undergrad years, I interned at INRIA Saclay, France (as part of my undergraduate thesis), Amazon and Wikimedia Foundation (as part of Google Summer of Code).
Email: mandikal[AT]cs.utexas.edu
CV /
Google Scholar /
GitHub
|
|
Publications
* denotes equal contribution
|
|
Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy
Priyanka Mandikal
Machine Learning for Ancient Languages (ACL Workshop), 2024
(Outstanding Paper Award)
webpage /
paper /
code /
dataset /
bibtex
|
|
ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projection
Arpit Bahety, Priyanka Mandikal, Ben Abbatematteo, Roberto Martín-Martín
Robotics: Science and Systems (RSS), 2024
(Outstanding Student Paper Award Finalist)
webpage /
paper /
bibtex
|
|
Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval
Priyanka Mandikal and Raymond Mooney
The 4th CEUR Workshop on Scientific Document Understanding (AAAI Workshop), 2024
paper /
bibtex
|
|
Learning Dexterous Robotic Grasping by Watching Humans in Action
Priyanka Mandikal
Master's Thesis, UT Austin, 2023
thesis
|
|
DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video
Priyanka Mandikal and Kristen Grauman
Conference on Robot Learning (CoRL), 2021
webpage /
paper /
bibtex
|
|
Learning Dexterous Grasping with Object-Centric Visual Affordances
Priyanka Mandikal and Kristen Grauman
IEEE International Conference on Robotics and Automation (ICRA), 2021
Lightning talk @ NeurIPS Workshop on Object Representations for Learning and Reasoning
webpage /
paper /
code /
bibtex
|
|
Cross-Conditioned Recurrent Networks for Long-Term Synthesis of
Inter-Person Human Motion Interactions
Jogendra Nath Kundu*, Himanshu Buckchash*, Priyanka Mandikal, Rahul M V, Anirudh Jamkhandi, R. Venkatesh Babu
Winter Conference on Applications of Computer Vision (WACV), 2020
paper /
bibtex
|
|
DIFFER: Moving Beyond 3D Reconstruction with Differentiable Feature Rendering
K L Navaneet, Priyanka Mandikal, Varun Jampani, R. Venkatesh Babu
Deep Generative Models for 3D Understanding (CVPR Workshop), Oral, 2019
paper /
code /
bibtex
|
|
Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network
Priyanka Mandikal and R. Venkatesh Babu
Winter Conference on Applications of Computer Vision (WACV), 2019
paper /
suppl /
code /
bibtex
|
|
CAPNet: Continuous Approximation Projection for 3D Point Cloud Reconstruction Using 2D Supervision
K L Navaneet*, Priyanka Mandikal*, Mayank Agarwal, R. Venkatesh Babu
AAAI Conference on Artificial Intelligence (AAAI), 2018
paper /
code /
bibtex
|
|
3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction
Priyanka Mandikal*, K L Navaneet*, R. Venkatesh Babu
3D Reconstruction Meets Semantics (ECCV Workshop), 2018
paper /
code /
bibtex
|
|
3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
Priyanka Mandikal*, Mayank Agarwal*, K L Navaneet*, R. Venkatesh Babu
British Machine Vision Conference (BMVC), 2018
paper /
code /
bibtex
|
|