AIConfPaper
← Search

Varun Ravi Kumar

6 accepted papers

2023

X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection

Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani +1
CVPR 2023poster

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of features from perspective view (PV) to a 3D world representati…

Cited by 35Source ↗PDF ↗Scholar ↗
2022

Detecting Adversarial Perturbations in Multi-Task Perception

Marvin Klingner, Varun Ravi Kumar, Senthil Yogamani, Andreas Bär, Tim Fingscheidt
IROS 2022poster

While deep neural networks (DNNs) achieve impressive performance on environment perception tasks, their sensitivity to adversarial perturbations limits their use in practical applications. In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception…

Cited by 23Source ↗code ↗Scholar ↗
2022

SynWoodScape: Synthetic Surround-View Fisheye Camera Dataset for Autonomous Driving

Ahmed Rida Sekkat, Yohan Dupuis, Varun Ravi Kumar, Hazem Rashed, Senthil Kumar Yogamani, Pascal Vasseur +1
RA-L 2022

Surround-view cameras are a primary sensor for automated driving, used for near-field perception. It is one of the most commonly used sensors in commercial vehicles primarily used for parking visualization and automated parking. Four fisheye cameras with a <inline-formula xmlns:mml="http://www.w3.or

Cited by 65Source ↗Scholar ↗
2021

OmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving

Varun Ravi Kumar, Senthil Kumar Yogamani, Hazem Rashed, Ganesh Sistu, Christian Witt, Isabelle Leang +2
RA-L 2021

Surround View fisheye cameras are commonly deployed in automated driving for 360 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> near-field sensing around the vehicle. This work presents a multi-task visual perception network on unrectified fish

Cited by 111Source ↗code ↗Scholar ↗
2020

FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Driving

Varun Ravi Kumar, Sandesh Athni Hiremath, Markus Bach, Stefan Milz, Christian Witt, Clément Pinard +2
ICRA 2020poster

Fisheye cameras are commonly used in applications like autonomous driving and surveillance to provide a large field of view (> 180o). However, they come at the cost of strong non-linear distortions which require more complex algorithms. In this paper, we explore Euclidean distance estimation on fish…

Cited by 85Source ↗Scholar ↗
2020

UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models

Varun Ravi Kumar, Senthil Yogamani, Markus Bach, Christian Witt, Stefan Milz, Patrick Mäder
IROS 2020poster

In classical computer vision, rectification is an integral part of multi-view depth estimation. It typically includes epipolar rectification and lens distortion correction. This process simplifies the depth estimation significantly, and thus it has been adopted in CNN approaches. However, rectificat…

Cited by 61Source ↗Scholar ↗