6 citations · 13 across the 14 of their papers we have counts for
15 papers
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within Datasets
Shubham Shrivastava, Xianling Zhang, Sushruth Nagesh +1
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…
Ref-DVGO: Reflection-Aware Direct Voxel Grid Optimization for an Improved Quality-Efficiency Trade-Off in Reflective Scene Reconstruction
Georgios Kouros, Minye Wu, Shubham Shrivastava +3
Neural Radiance Fields (NeRFs) have revolutionized the field of novel view synthesis, demonstrating remarkable performance. However, the modeling and rendering of reflective object…
DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions
Stephen Hausler, Sourav Garg, Punarjay Chakravarty +3
Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior m…
Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization
Stephen Hausler, Sourav Garg, Punarjay Chakravarty +3
Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects…
Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation
Georgios Kouros, Shubham Shrivastava, Cédric Picron +3
Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivi…
Improving Worst Case Visual Localization Coverage via Place-specific Sub-selection in Multi-camera Systems
Stephen Hausler, Ming Xu, Sourav Garg +4
6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map. Current techniques use hierarch…
QAGAN: Adversarial Approach To Learning Domain Invariant Language Features
Shubham Shrivastava, Kaiyue Wang
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical p…
Propagating State Uncertainty Through Trajectory Forecasting
Boris Ivanovic, Yifeng Lin, Shubham Shrivastava +2
Uncertainty pervades through the modern robotic autonomy stack, with nearly every component (e.g., sensors, detection, classification, tracking, behavior prediction) producing cont…
VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction
Shubham Shrivastava
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot percepti…
Meta-Regularization by Enforcing Mutual-Exclusiveness
Edwin Pan, Pankaj Rajak, Shubham Shrivastava
Meta-learning models have two objectives. First, they need to be able to make predictions over a range of task distributions while utilizing only a small amount of training data. S…
S-BEV: Semantic Birds-Eye View Representation for Weather and Lighting Invariant 3-DoF Localization
Mokshith Voodarla, Shubham Shrivastava, Sagar Manglani +3
We describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization. A topological map of S-BEV signatur…
An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation
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, foll…
Sim2Real for Self-Supervised Monocular Depth and Segmentation
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…
CubifAE-3D: Monocular Camera Space Cubification for Auto-Encoder based 3D Object Detection
Shubham Shrivastava, Punarjay Chakravarty
We introduce a method for 3D object detection using a single monocular image. Starting from a synthetic dataset, we pre-train an RGB-to-Depth Auto-Encoder (AE). The embedding learn…
Deflating Dataset Bias Using Synthetic Data Augmentation
Nikita Jaipuria, Xianling Zhang, Rohan Bhasin +5
Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardwa…