Resume (1 Page) |  Resume (2 Page) | Publications | GitHub | Google Scholar | Semantic Scholar | Linkedin | Twitter | Youtube | OpenReview | DBLP | Instagram | Facebook | Quora 

Welcome! My name is Abhinav Kumar. I am a PhD student candidate in the Computer Vision Lab, Department of Computer Science at Michigan State University (MSU), working with Prof Xiaoming Liu. My research interests are 3D Detection, 3D Reconstruction and 3D Computer Vision. applied to Autonomous Driving, AR/VR, Embodied AI and Robotics.

My past research internships were at Bosch AI Research, Sunnyvale, CA, with Dr Yuliang Guo and Dr Liu Ren,  Facebook AI Research (FAIR), Menlo Park, CA, with Dr Georgia Gkioxari and Dr Garrick Brazil, and Mitsubishi Electric Research Labs (MERL), Cambridge, MA, with Dr Tim Marks, Dr Michael Jones, and Dr Anoop Cherian.

During 2016-2018, I was a Research Engineer at Xerox Research Centre India, Bangalore, with Dr Sriganesh Madhvanath and Vladimir Kozitksy.  I hold a Masters in Signal Processing  and Bachelors in Electrical Engineering  from Indian Institute of Technology (IIT) Bombay and IIT Patna, respectively.  My Masters advisor was Prof Animesh Kumar.  I attended Jawahar Vidya Mandir, Shyamali, Ranchi and MK DAV Public School, Chianki, Daltonganj.

Publications

 Google Scholar / Semantic Scholar / DBLP / OpenReview
* = Equal Contributions

Selected Papers

CVPR / ECCV / ICCV / NeurIPS are among top 5 conferences in all computer science [Source].

SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Object Detection of Large Objects

Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren and Xiaoming Liu
CVPR 2024
pdf / supplementary / 5min talk / slides / poster / demo / arxiv / code / project

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

Garrick Brazil, Abhinav Kumar, Julian Straub, Nikhila Ravi, Justin Johnson  and Georgia Gkioxari
CVPR 2023
pdf / supplementary / 5min talk / slides / poster / demo / arxiv / code / project 

DEVIANT: Depth Equivariant Network for Monocular 3D Object Detection

Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami  and Xiaoming Liu
ECCV 2022
pdf / supplementary / 5min talk / slides / poster / demo / arxiv / code / project 

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

Abhinav Kumar, Garrick Brazil and Xiaoming Liu
CVPR 2021
pdf / supplementary / 5min talk / slides / poster / demo / arxiv / code / project

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

Abhinav Kumar*, Tim Marks*,  Wenxuan Mou*, Ye Wang, Michael Jones, Anoop Cherian, Toshiaki Koike-Akino, Xiaoming Liu and Chen Feng
CVPR 2020
pdf / supplementary / 1min talk / slides / demo / arxiv / code / dataset

Other Papers

SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction

Yuliang Guo, Abhinav Kumar,  Chen Zhao, Ruoyu Wang, Xinyu Huang, and Liu Ren
ECCV 2024
pdf / poster / 5min talk / demo / arxiv / code / project 

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

Shengjie Zhu, Abhinav Kumar,  Masa Hu and Xiaoming Liu
NeurIPS 2023
pdf / poster / demo / arxiv / code / openreview

PrObeD: Proactive 2D Object Detection Wrapper

Vishal Asnani, Abhinav Kumar, Sua You and Xiaoming Liu
NeurIPS 2023
pdf / arxiv / code  / openreview 

RADIANT: RADar Image Association NeTwork for 3D Object Detection

Yunfei Long, Abhinav Kumar, Daniel Morris, Xiaoming Liu, Marcos Castro and Punarjay Chakravarty
AAAI 2023
pdf / code  / slides  / poster 

Scaling Up Exact Neural Network Compression by ReLU Stability

Thiago Serra, Xin Yu, Abhinav Kumar and Srikumar Ramalingam
NeurIPS 2021
pdf / supplementary / talk  / arxiv / code / openreview 

Lossless Compression of Deep Neural Networks

Thiago Serra, Abhinav Kumar and Srikumar Ramalingam
CPAIOR 2020  and ICML LXAI Workshop 2020
pdf / slides / talk / poster / code

Zero Shot License Plate Re-Identification

Mayank Gupta*, Abhinav Kumar* and Sriganesh Madhvanath
WACV 2019  (Spotlight)
pdf / slides / poster / article

Fast and Generalisable License Plate Re-Identification using Neural Embedding of Fisher Vectors

Abhinav Kumar*, Shantanu Gupta*, Vladimir Kozitksy and Sriganesh Madhvanath
ICVGIP 2018 (Short Oral)
pdf / slides / arxiv

VPDS: An AI-based Automated Vehicle Occupancy and Violation Detection System

Abhinav Kumar*, Aishwarya Gupta*, Bishal Santra*, Lalitha Srinivasan*, Manasa Kolla*, Mayank Gupta* and  Rishabh Singh*
IAAI (Application conference of AAAI) 2019
pdf / slides / article / tutorial  / bronchure

Workshops and Arxived

UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss

Abhinav Kumar*, Tim Marks*,  Wenxuan Mou*, Chen Feng and Xiaoming Liu
ICCV Workshops on Statistical Deep Learning in Computer Vision 2019
pdf / slides / poster / media / Best Oral Presentation award

Equivalent and Approximate Transformations of Deep Neural Networks

Abhinav Kumar, Thiago Serra and Srikumar Ramalingam
pdf / talk  / code

Parametric Synthesis of Text on Stylized Backgrounds using PGGANs

Mayank Gupta, Abhinav Kumar and Sriganesh Madhvanath
pdf / demo

Estimation of Bandlimited Grayscale Images From the Single Bit Observations of Pixels Affected by Additive Gaussian Noise

Abhinav Kumar and Animesh Kumar
pdf / slides / report

SmartEvacTrack: A People Counting and Coarse-level Localisation Solution for Efficient Evacuation of Large Buildings

Nasim Ahmed, Avik Ghose, Amit Agarrwal, Chirabrata Bhaumik, Vivek Chandel and Abhinav Kumar
PERCOM Workshops on Crowd Assisted Sensing, Pervasive Systems and Communications 2015
link

Technology Enabled Assessment Environment

Rohit Kondekar, Pravin Kondekar, Deepak Phatak, Avinash Awate, Mayank Singh, Alefiya Lightwalla and Abhinav Kumar
IASTED International Conference on Technology for Education 2011
link / report

Patents

GrooMeD-NMS for Monocular 3D Object Detection

Xiaoming Liu, Abhinav Kumar and Garrick Brazil
US Patent filed 2021
link

Image Processing System and Method for Landmark Location Estimation with Uncertainty

Tim Marks,  Abhinav Kumar, Wenxuan Mou, Chen Feng and Xiaoming Liu
US  11,127,164 B2, granted 2021
link

Estimation of Direction of Motion of Users on Mobile Devices 

Avik Ghose, Abhinav Kumar, Chirabrata Bhaumik and Arpan Pal
US 10,520,330 B2, granted 2019
link

Talks

Generalizing Monocular 3D Object Detection

Mathematical Modeling for Landmark and 3D Object Detection

Service+Teaching

Reviewer

Journals 

Conferences 

Awards 

Teaching Assistant