147 citations · 603 across the 30 of their papers we have counts for
6 papers · 1 filter
GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions
Sanket Kalwar, Dhruv Patel, Aakash Aanegola +3
Detecting objects under adverse weather and lighting conditions is crucial for the safe and continuous operation of an autonomous vehicle, and remains an unsolved problem. We prese…
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…
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation
Madhu Vankadari, Stuart Golodetz, Sourav Garg +3
Self-supervised deep learning methods for joint depth and ego-motion estimation can yield accurate trajectories without needing ground-truth training data. However, as they typical…
Improving Road Segmentation in Challenging Domains Using Similar Place Priors
Connor Malone, Sourav Garg, Ming Xu +2
Road segmentation in challenging domains, such as night, snow or rain, is a difficult task. Most current approaches boost performance using fine-tuning, domain adaptation, style tr…
ReF -- Rotation Equivariant Features for Local Feature Matching
Abhishek Peri, Kinal Mehta, Avneesh Mishra +3
Sparse local feature matching is pivotal for many computer vision and robotics tasks. To improve their invariance to challenging appearance conditions and viewing angles, and hence…
MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
Ahmad Khaliq, Michael Milford, Sourav Garg
Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypo…