Anushka Agarwal

I'm a Computer Science Masters student at UMass Amherst, specializing in 3D/4D computer vision, Gaussian Splatting, video diffusion models, and embodied AI. My work focuses on building intelligent systems that understand, reconstruct, and generate dynamic 3D scenes.

I am always open to discuss potential research collaborations in 3D/4D and related fields. Feel free to email me to discuss potential collaborations.

Email / Google Scholar / GitHub / LinkedIn / Resume

RECENT UPDATES

[Sept 2025] Wrapped up an amazing summer at Flawless AI
[July 2025] Presented my work GenSync at CVPR Workshop AI4CC
[Sep 2024] Started my Masters at Umass Amherst

WORK EXPERIENCE

I am fortunate to have worked at the following places:

	Research Engineering Intern (CW) Flawless AI Santa Monica, CA, USA (May2025 - September 2025) Worked with Video Difussion for Lip-Sync and Video Generation.
	Machine Learning Researcher NeuralGarage Bangalore, India (Jan 2023 - August 2024) Worked with 3D model for Video Generation
	Student Researcher Air Lab, Carnegie Mellon University Remote (Sept/2021 - June/2023) Advisor: Sebastian Scherer

PUBLICATIONS/SUBMISSIONS

	PackUV: Packed Gaussian UV Maps for 4D Volumetric Video Aashish Rai, Angela Xing, Anushka Agarwal, Xiaoyan Cong, Zekun Li, Tao Lu, Srinath Sridhar In submission...
	GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting Anushka Agarwal , Muhammad Yusuf Hassan, Talha Chafekar CVPR Workshop 2025 AI4CC project page \| pdf

[Brown University] Research Collaboration on 3D Vision Interactive 3D Vision & Learning Lab

(website template modified from repo )

Hey folks from around the globe!!