Aniruddha Mahapatra

Research Engineer
Adobe Inc.

anmahapa@adobe.com
Google Scholar
@aniruddha26398
github.com/anime26398
linkedin.com/in/aniruddha98

I am a Research Engineer at Adobe Research. I completed my Masters in Computer Vision (MSCV) from Carnegie Mellon University, where I was advised by Prof. Jun-Yan Zhu. My research interest include image and video synthesis and editing using generative models.

I am fortunate to have worked with Aliaksandr Siarohin, Hsin-Ying Lee and Sergey Tulyakov at Snap Research, Kuldeep Kulkarni, Anandhavelu Natarajan and Subrata Mitra at Adobe Research, Jitendra Singh at IBM Research, and, Professor Biplab Banerjee and Ranita Biswas at Indian Institute of Technology, Roorkee.

Software

Firefly Video [Adobe]

Key contributor to the design of the video tokenizer and decoder architecture for Adobe's Firefly Video foundation model.

Website

Generative Extend [Adobe]

Key contributor to the specialized decoder architecture and optimizations that enables fast and High-Resolution decoding.

Website

Moving Elements [Adobe]

Adobe's Photoshop Elements 2023 new feature 'Moving Elements' lets users generate aesthetic cinemagraphs from their photos.

Website

Publications

arXiv 2025

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

Yitian Zhang, Long Mai, Aniruddha Mahapatra, David Bourgin, Yicong Hong, Jonah Casebeer, Feng Liu, Yun Fu

Paper Website

arXiv 2025

Progressive Growing of Video Tokenizers for Highly Compressed Latent Spaces

Aniruddha Mahapatra, Long Mai, Yitian Zhang, David Bourgin, Feng Liu

Paper Website

ECCV 2024

Co-speech Gesture Video Generation with 3D Human Meshess

Aniruddha Mahapatra*, Richa Mishra*, Renda Li, Ziyi Chen, Boyang Ding, Shoulei Wang, Jun-Yan Zhu, Peng Chang, Mei Han, Jing Xiao

Paper Website

CVPR 2024

On the Content Bias in Fréchet Video Distance

Songwei Ge, Aniruddha Mahapatra, Gaurav Parmar, Jun-Yan Zhu, Jia-Bin Huang

Paper Website Code

SIGGRAPH Asia (ACM Transactions on Graphics) 2023

Text-Guided Synthesis of Eulerian Cinemagraphs

Aniruddha Mahapatra, Aliaksandr Siarohin, Hsin-Ying Lee,Sergey Tulyakov, Jun-Yan Zhu

Paper Website Code

CVPR 2022

Controllable Animation of Fluid Elements in Still Images

Aniruddha Mahapatra, Kuldeep Kulkarni

Paper Website

WACV 2023

GEMS: Scene Expansion using Generative Models of Graphs

Aniruddha Mahapatra*, Rishi Agarwal*, Tirupati Saketh Chandra*, Vaidehi Patil*, Kuldeep Kulkarni, Vishwa Vinay

Paper

Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models

EMNLP 2022

⭐ Oral

Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models

Aniruddha Mahapatra, Snarmila Nangi, Aparna Garimella, Anandhavelu Natarajan

Paper

ICCV 2019

SemIE: Semantically-aware Image Extrapolation

Bholeshwar Khurana, Soumya Ranjan Dash, Abhishek Bhatia, Aniruddha Mahapatra, Hrituraj Singh, Kuldeep Kulkarni

Paper Website

Experience

2024—Present

Adobe Research

Research Engineer

Developing high quality video generative models. Currenlty working on efficient and compact latent space for video generation and adding more controllable features to the model.

Manager: Feng Liu

Summer 2023

Snap Research

Research Scientist Intern

Worked on trajectory controlled video generation.

Manager: Aliaksandr Siarohin

2020—2022

Adobe Research

Research Associate

Worked on controllable cinemagraph generation and named entity extraction.

Manager: Balaji Srinivasan

Summer 2019

Adobe Research

Research Intern

Worked on action recognition and action localization in videos on edge devices.

Manager: Subrata Mitra

Education

2022—2023

Carnegie Mellon University

Master of Science in Computer Vision (MSCV)

Advisor: Prof. Jun-Yan Zhu

2016—2020

Indian Institute of Technology, Roorkee (IITR)

B. Tech in Computer Science and Engineering

Thesis Advisor: Prof. Balasubramanian Raman