I am a Ph.D. candidate at The Robotics Institute, Carnegie Mellon University advised by Prof. Deva Ramanan. My research focus is broadly on spatiotemporal 4D scene understanding and its applications. Previously, during my Masters at CMU RI, I worked on estimating and exploiting 3D scene geometry from single images, to reason about occlusions and densify sparse depth input. I hold a B.E. degree in Computer Engineering from the University of Delhi and have had the fortune to work at amazing companies - Boston Dynamics AI Institute, Google Research, Argo AI, Staqu Technologies.

I am a trained Kathak dancer, and Hindustani classical vocalist. I love baking, taking care of plants, and hiking. My life is made easier by my husband, Akash Sharma, who does research in robotics.

[03/24] We launched the 2nd iteration of Argoverse2.0 Occupancy Forecasting Challenge.
[02/24] I'll be at the Boston Dynamics AI Institute this summer.
[08/23] I was chosen as a Rising Star in EECS!
[07/23] I gave a talk on building 4D foundation models at Waabi AI.
[06/23] We are all set to organize the Argoverse2.0 Challenges at CVPR 2023!
[03/23] Our work on 4D occupancy forecasting was accepted to CVPR 2023!
[07/22] Detecting Invisible People was covered by NBC Universal.
[01/22] I'll be at Google Research this summer, working with Alireza Fathi and Cordelia Schmid!
[07/21] My favorite work, Detecting Invisible People, was accepted to ICCV '21!
[04/21] I accepted CMU's PhD offer for Fall '21.
[07/20] The ECCV TAO Challenge is now live.
[07/20] TAO was accepted to ECCV '20 as a spotlight paper! Check out the manuscript.
[04/20] I'll be at Argo AI for the summer as a Research Intern.
[02/20] Our workshop titled, 'Object Tracking and its Many Guises' was accepted at ECCV 2020.

CV   /   Google Scholar   /   tarasha@cmu.edu

	Predicting Long-horizon Futures by Conditioning on Geometry and Time Tarasha Khurana, Deva Ramanan Under submission. [pdf] [project page] [code]
	TAO-Amodal: A Benchmark for Tracking any Object Amodally Cheng-Yen Hseih, Kaihua Chen, Achal Dave, Tarasha Khurana, Deva Ramanan Under submission. [pdf] [project page] [code]
	Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting Tarasha Khurana, Peiyun Hu, David Held, Deva Ramanan IEEE/CVF Conferece on Computer Vision and Pattern Recognition (CVPR), '23. [pdf] [project page] [code]
	Differentiable Raycasting for Self-supervised Planning Tarasha Khurana*, Peiyun Hu*, Achal Dave, Jason Ziglar, David Held, Deva Ramanan European Conference on Computer Vision (ECCV), '22. [pdf] [project page] [code]
	BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Videos Ali Athar, Jonathon Luiten, Paul Voigtlaender, Tarasha Khurana, Achal Dave, Bastian Leibe, Deva Ramanan IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023. [arXiv] [benchmark & API]
	Detecting Invisible People Tarasha Khurana, Achal Dave, Deva Ramanan International Conference on Computer Vision (ICCV), '21. [arXiv] [project page] [code]
	Detecting Invisible People's media coverage by NBC Universal. [article]
	TAO: A Large-Scale Benchmark for Tracking Any Object Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan European Conference on Computer Vision (ECCV) '20. Spotlight. [arXiv] [project page] [workshop] [dataset]
	Exploiting Texture Cues for Clothing Parsing in Fashion Images Tarasha Khurana, Kushagra Mahajan, Chetan Arora, Atul Rai 25th IEEE International Conference on Image Processing (ICIP) '18. [pdf] [poster] [Xplore]
	Pose Aware Fine Grained Visual Classification Using Pose Experts Kushagra Mahajan, Tarasha Khurana, Ayush Chopra, Isha Gupta, Chetan Arora, Atul Rai 25th IEEE International Conference on Image Processing (ICIP) '18. [pdf] [poster] [Xplore]