Pradyumna Chari

Email  /  Google Scholar  /  Twitter  /  LinkedIn

profile photo

About Me

I am a fifth year PhD student at the Visual Machines Group, UCLA, advised by Prof. Achuta Kadambi. At VMG, we work on developing cutting-edge tools at the intersection of physics and artificial intelligence, to be applied to diverse problems in human-centric computer vision and computational imaging. I have been fortunate to be supported by a CISCO PhD Fellowship for a part of my PhD.

I completed my Bachelor's degree in Electrical Engineering from the Indian Institute of Technology, Madras, India, where I was the President's Gold Medal awardee for outstanding academic performance, for the year 2019. I worked on my undergraduate thesis with Prof. Kaushik Mitra at the Computational Imaging Lab in the domain of High Dynamic Range imaging.

Updates

  • July 2024: Two papers accepted to ECCV 2024.

  • April 2024: Feature 3DGS is chosen as a CVPR 2024 highlight paper (Top 2.8%).

  • December 2023: Three new preprints on 3D Gaussian splatting and generative methods.

  • July 2023: Summer internship at Snap Research.

  • June 2023: Invited talk at Rice Univeristy.

  • March 2023: Paper accepted to IEEE Access.

  • November 2022: Our UIST 2022 work, ForceSight, receives Best Demo Honorable Mention.

  • September 2022: SIGGRAPH 2022 work on equitable computational imaging for heart rate estimation featured by Daily Bruin.

  • August 2022: SIGGRAPH 2022 work on equitable computational imaging for heart rate estimation featured by UCLA Newsroom.

  • August 2022: Paper accepted to UIST 2022.

  • July 2022: Paper accepted to ECCV 2022.

  • May 2022: Paper accepted to SIGGRAPH 2022.

  • March 2022: Paper accepted to CVPR 2022.

  • August 2021: Awarded the CISCO PhD Fellowship for work in remote health sensing.

  • October 2020: Our paper, Diverse RPPG: Camera-based Heart Rate Estimation for Diverse Subject Skin Tones and Scenes, is up on ArXiv.

  • October 2019: Awarded the President of India Prize, Bharat Ratna M Visvesvaraya Memorial Prize and the Siemens Prize for outstanding academic performance from IIT Madras.
    Media and Links: IIT Madras, UCLA, The Hindu, Jagranjosh

  • March 2019: Awarded the Graduate Dean's Scholars Award from the University of California, Los Angeles in 2019, in recognition of prior academic excellence.

Research

My research interests lie at the intersection computer vision/computational imaging and learning models at scale. My current work relates to developing tools for rendering and 3D representation in the era of novel generative priors. I am also interested in aspects of fairness in the era of learning-based vision systems and equitable health sensing.

In the past, I have worked on more traditional imaging projects. As part of my undergraduate thesis, I worked on developing novel regimes for HDR imaging with new camera setups. I have also worked on minor projects in lensless imaging and camera calibration regimes for large camera networks.

Selected Papers

* indicates equal contribution

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Shijie Zhou, Haoran Chang*, Sicheng Jiang*, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi
CVPR, 2024 (Highlight paper, top 2.8%)

Feature 3DGS distills feature fields from 2D foundation models, opening the door to a brand new semantic, editable, and promptable explicit 3D scene representation.


Project Webpage
CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting
Alexander Vilesov*, Pradyumna Chari*, Achuta Kadambi
ArXiv, 2023

A method for 3D generation of multi-object realistic scenes from text by utilizing text-to-image diffusion models and Gaussian radiance fields. These scenes are decomposable and editable at the object level.


Project Webpage
SparseGS: Real-Time 360° Sparse View Synthesis using Gaussian Splatting
Haolin Xiong*, Sairisheek Muttukuru*, Rishi Upadhyay, Pradyumna Chari, Achuta Kadambi
ArXiv, 2023

A framework that leverages explicit radiance fields, monocular depth cues, and generative priors to enable 360° sparse view synthesis using 3D Gaussian Splatting.


Project Webpage
On Learning Mechanical Laws of Motion from Video Using Neural Networks
Pradyumna Chari, Yunhao Ba, Shijie Zhou, Chinmay Talegaonkar, Shreeram Athreya, Achuta Kadambi
IEEE Access, 2023

A novel pipeline that enables discovery of underlying parameters and equations from videos of physical phenomena.


Project Webpage
Forcesight: Non-contact force sensing with laser speckle imaging
Siyou Pei, Pradyumna Chari, Xue Wang, Xiaoying Yang, Achuta Kadambi Yang Zhang
UIST, 2022, Best Demo Honorable Mention

Using laser speckle imaging for touch and force sensing on surfaces in the wild.


Paper
MIME: Minority Inclusion for Majority Group Enhancement of AI Performance
Pradyumna Chari, Yunhao Ba, Shreeram Athreya, Achuta Kadambi
ECCV, 2022

Some inclusion of minority samples improves test error for the majority group.


Project Webpage
Blending Camera and 77 GHz Radar Sensing for Equitable, Robust Plethysmography
Alexander Vilesov*, Pradyumna Chari*, Adnan Armouti*, Anirudh B H, Kimaya Kulkarni, Ananya Deoghare, Laleh Jalilian, Achuta Kadambi
ACM Trans. Graph. (SIGGRAPH), 2022

A multimodal fusion approach between camera and radar to achieve more equitable and robust plethysmography.


Project Webpage
Synthetic Generation of Face Videos with Plethysmograph Physiology
Zhen Wang*, Yunhao Ba*, Pradyumna Chari, Oyku Deniz Bozkurt, Gianna Brown, Parth Patwa, Niranjan Vaddi, Laleh Jalilian, Achuta Kadambi
CVPR, 2022

A scalable biophysical neural rendering method to generate biorealistic synthetic rPPG videos given any reference image and target rPPG signal as input.


Project Webpage
Diverse RPPG: Camera-based Heart Rate Estimation for Diverse Subject Skin Tones and Scenes
Pradyumna Chari*, Krish Kabra*, Doruk Karinca, Soumyarup Lahiri, Diplav Srivastava, Kimaya Kulkarni, Tianyuan Chen, Maxime Cannesson, Laleh Jalilian, Achuta Kadambi
ArXiv, 2020

Identifying and solving underlying bias in remote heart rate monitoring using consumer camera systems based on noise analysis.


Project Webpage

Template credits: Jon Barron