Agniv Chatterjee

Agniv Chatterjee

Ph.D. Student @ UT Austin | Computer Vision Researcher


Email Scholar GitHub LinkedIn Resume

About Me

I am a 2nd year doctoral student at the University of Texas at Austin, under the supervision of Dr. Georgios Pavlakos. My research currently focuses on understanding how humans interact with their surroundings, especially with objects, and how this interaction can be quantified using 3D representations.

I have worked on various projects in the fields of Human-Object Interaction, Pose Classification and Contact Estimation, Tiny Object Detection and Classification, Audio Classification, and Biomedical Image Segmentation. I am open to working on new projects on topics both known and unexplored by me.

Experience

University of Texas at Austin


Dept of Computer Science

Graduate Research Assistant

Working on the joint reconstruction of full-body humans and objects from natural images under Dr. Georgios Pavlakos.

Max Planck Institute for Intelligent Systems, Tübingen

Perceiving Systems

Undergraduate Research Intern

Developed a discrete contact annotation tool for vertex-level contact annotation under Dr. Michael Black. Created a vertex-level human contact dataset and developed a framework for detecting contact from natural images of humans (ICCV 2023).


Subsequently, worked on joint reconstruction of human and object meshes from natural images given their contact regions (CVPR 2025).

INRIA, Sophia Antipolis


STARS Team

Undergraduate Research Intern

Developed a combined detection-classification pipeline for High-Resolution images of Trichogramma wasps (VISAPP 2023).

Indian Institute of Science


Spire Lab

Undergraduate Research Intern

Developed a framework for the diagnosis of patients as ALS/PD or Normal, based on phoneme utterance audios, under Dr. Prasanta Ghosh.

Indian Institute of Technology, Delhi

Undergraduate Research Intern

Developed a framework for Automatic Pose Identification and Recommendation for Yoga asanas under Dr. Brejesh Lall.

Department of Electrical Engineering

Undergraduate Research Assistant

Performed independent research under Dr. Debangshu Dey on Glaucoma detection using deep learning methods (Published in Biomedical Signal Processing and Control, Elsevier).

Education

University of Texas at Austin

August 2024 - Present

Ph.D. in Computer Science

GPA: 4.0/4.0

Jadavpur University

Sept 2019 - June 2023

Bachelor of Electrical Engineering

CGPA: 8.7/10.0

Publications

DECO Teaser

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

Proposed a pipeline to infer dense 3D contact on the human body using scene and body-part context. Also curated a dataset with in-the-wild images and crowdsourced dense 3D contact annotations.

Accepted at International Conference on Computer Vision (ICCV), 2023 (Oral).

TrichANet Visual

TrichANet: An Attentive Network for Trichogramma Classification

Proposed a combined detection-classification pipeline for the detection of tiny wasps from images, and subsequent classification into species.

Accepted for oral presentation at VISAPP 2023.

PICO Teaser

PICO: Reconstructing 3D People In Contact with Objects

Proposed a framework for joint human-object reconstruction in 3D, using an optimization-based method guided by contact constraints.

Accepted at CVPR 2025.

ISBI Visual

Consistency Regularization Method for Semi-Supervised Medical Image Segmentation

The proposed method leverages segmentation of the interpolation of two unlabeled data for Semi-Supervised Cardiac MRI segmentation.

Accepted at IEEE ISBI, 2022.

PY-Net Visual

PY-Net: Rethinking Segmentation Frameworks with Dense Pyramidal Operations

A pipeline with auxiliary and densely-connected pyramidal decoder for segmentation of the Optic Disc and Cup from Optical Fundus images.

Published in Biomedical Signal Processing and Control, Elsevier.

Skills

Python PyTorch TensorFlow Keras Java MATLAB

Git LaTeX HTML/CSS JavaScript Dash/Plotly

Perspective

Machine Learning xkcd

Image courtesy of xkcd