1 code implementation • 19 Aug 2023 • Shubham Shrivastava, Xianling Zhang, Sushruth Nagesh, Armin Parchami
Data imbalance is a well-known issue in the field of machine learning, attributable to the cost of data collection, the difficulty of labeling, and the geographical distribution of the data.
1 code implementation • 16 Aug 2023 • Georgios Kouros, Minye Wu, Shubham Shrivastava, Sushruth Nagesh, Punarjay Chakravarty, Tinne Tuytelaars
To this end, we investigate an implicit-explicit approach based on conventional volume rendering to enhance the reconstruction quality and accelerate the training and rendering processes.
no code implementations • 30 Jun 2023 • Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences.
no code implementations • 30 Jun 2023 • Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline.
1 code implementation • 12 Aug 2022 • Georgios Kouros, Shubham Shrivastava, Cédric Picron, Sushruth Nagesh, Punarjay Chakravarty, Tinne Tuytelaars
In both cases, the idea is to directly predict the pose of an object.
no code implementations • 28 Jun 2022 • Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map.
1 code implementation • 24 Jun 2022 • Shubham Shrivastava, Kaiyue Wang
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry.
1 code implementation • 7 Oct 2021 • Boris Ivanovic, Yifeng Lin, Shubham Shrivastava, Punarjay Chakravarty, Marco Pavone
As a result, perceptual uncertainties are not propagated through forecasting and predictions are frequently overconfident.
1 code implementation • 13 Apr 2021 • Shubham Shrivastava
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving.
1 code implementation • 24 Jan 2021 • Edwin Pan, Pankaj Rajak, Shubham Shrivastava
Second, they also need to adapt to new novel unseen tasks at meta-test time again by using only a small amount of training data from that task.
no code implementations • 23 Jan 2021 • Mokshith Voodarla, Shubham Shrivastava, Sagar Manglani, Ankit Vora, Siddharth Agarwal, Punarjay Chakravarty
We describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization.
no code implementations • 5 Jan 2021 • Kaushik Balakrishnan, Punarjay Chakravarty, Shubham Shrivastava
Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control.
1 code implementation • 1 Dec 2020 • Nithin Raghavan, Punarjay Chakravarty, Shubham Shrivastava
Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly.
no code implementations • 7 Jun 2020 • Shubham Shrivastava, Punarjay Chakravarty
We introduce a method for 3D object detection using a single monocular image.
3D Object Detection From Monocular Images Autonomous Vehicles +3
no code implementations • 28 Apr 2020 • Nikita Jaipuria, Xianling Zhang, Rohan Bhasin, Mayar Arafa, Punarjay Chakravarty, Shubham Shrivastava, Sagar Manglani, Vidya N. Murali
Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware.