N Dinesh Reddy
Scientist, AWS AI, Amazon
Location: Amazon SJC25
Email: dnarapur [at] amazon (dot) com
Resume
Google Scholar
DBLP
Twitter
I am working as Scientist at AWS AI Labs in Santa Clara. I graduated with a PHD in Robotics from Robotic Institute, School of Computer Science, Carnegie Mellon University. My thesis was on Self-Supervising Occlusion For Vision I was awarded Amazon Go PHD Fellowship and 2021 Qualcomm Innovation Fellowship during my PHD studies and am a recipient of 2021 IEEE IV Best paper award.
Internships: I am always looking for strong graduate students to collaborate with. If you are interested in interning at Amazon AWS AI with me, send me an email detailing what your research interests are, and what you would like to work on during the internship.
Press Coverage
News
- [Mar 2024] One paper accepted to CVPR 2024 as Oral(top 90 out of 11532).
- [Feb 2024] One paper accepted to ICRA 2024
- [Feb 2023] Two papers accepted to CVPR 2023.
- [Dec 2022] I Successfully defended thanks to my committee members Srinivasa Narasimhan
- [May 2022] Selected to BITS 30Under30 award. More details can be found here
- [Feb 2022] Our Work on WALT has been accepted to CVPR 2022. New orleans here we come
- [July 2021] Traffic4D has won the best paper award at IVS2021
- [June 2021] Awarded 2021 Qualcomm Innovation Fellowship, check out the press release
- [Dec 2019] Awarded Amazon Go PHD Fellowship
Publications
WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion
Khiem Vuong, N Dinesh Reddy, Robert Tamburo and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2024
[PDF] [Project Page] [5Min Talk][Code] [Dataset] [BibTex]
Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
Siddharth Tourani, Jayaram Reddy, Sarvesh Thakur, K Madhava Krishna, Muhammad Haris Khan, N Dinesh Reddy
In IEEE International Conference on Robotics and Automation (ICRA) 2024
Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
Anurag Ghosh, N Dinesh Reddy, Christoph Mertz and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[PDF] [Project Page] [Code]
RAC: Reconstructing Animatable Categories from Videos
Gengshan Yang, Chaoyang Wang, N Dinesh Reddy, and Deva Ramanan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[Project Page]
WALT:Watch And Learn 2d amodal representation from Time-lapse imagery
N Dinesh Reddy, Robert Tamburo and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2022
[PDF] [Project Page] [Supp] [Poster][5Min Talk][Code] [Dataset] [BibTex]
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
N Dinesh Reddy, Laurent Guigues, Leonid Pischulini, Jayan Eledath and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2021
[PDF] [Project Page] [Supp] [Poster] [Video] [5Min Talk] [BibTex]
Traffic4D: Single View Longitudinal 4D Reconstruction of Repetitious Activity using Self-Supervised Experts
Fangyu Li, N. Dinesh Reddy, Xudong Chen and Srinivasa G. Narasimhan
In IEEE Intelligent Vehicles Symposium (IV) 2021
Best Paper Award
[PDF] [Project Page] [Poster] [12Min Talk] [Code] [Dataset] [BibTex]
Diffraction Line Imaging
Mark Shenin, N Dinesh Reddy, Matthew O'Toole, and Srinivasa Narasimhan
In European Conference on Computer Vision (ECCV) 2020 (ORAL)
[PDF] [Project Page] [Supp] [Video] [Video Long] [BibTex]
Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks
N Dinesh Reddy, Minh Vo, and Srinivasa Narasimhan
In International Conference on Computer vision and pattern recognition (CVPR) 2019
[PDF] [Project Page] [Poster] [Supp] [Dataset] [Code] [BibTex]
CarFusion: Combining Part Detection and Point Tracking for Dynamic 3D Reconstruction of Vehicles
N Dinesh Reddy, Minh Vo, and Srinivasa Narasimhan
In International Conference on Computer vision and pattern recognition (CVPR) 2018
[PDF] [Project Page] [Poster] [Dataset] [Supp] [Video] [BibTex]
Dynamic Body VSLAM with Semantic Constraints
N Dinesh Reddy,Prateek Singhal, Visesh Chari and K Madhava Krishna
In IEEE International Conference on Intelligent Robots and Systems (IROS) 2015
[PDF] [Project Page] [Dataset] [Video] [BibTex]
Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
Anurag Ghosh, N Dinesh Reddy, Christoph Mertz and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2023
RAC: Reconstructing Animatable Categories from Videos
Gengshan Yang, Chaoyang Wang, N Dinesh Reddy, and Deva Ramanan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2023
2022
WALT:Watch And Learn 2d amodal representation from Time-lapse imagery
N Dinesh Reddy, Robert Tamburo and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2022
[PDF] [Project Page] [Supp] [Poster][5Min Talk][Code] [Dataset] [BibTex]
2021
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
N Dinesh Reddy, Laurent Guigues, Leonid Pischulini, Jayan Eledath and Srinivasa Narasimhan
In International Conference on Computer Vision and Pattern Recognition (CVPR) 2021
[PDF] [Project Page] [Supp] [Poster] [Video], [5Min Talk] [BibTex]
Traffic4D: Single View Longitudinal 4D Reconstruction of Repetitious Activity using Self-Supervised Experts
Fangyu Li, N. Dinesh Reddy, Xudong Chen and Srinivasa G. Narasimhan
In IEEE Intelligent Vehicles Symposium (IV) 2021
[PDF] [Project Page] [Slides] [Poster] [12Min Talk] [BibTex]
2020
Diffraction Line Imaging
Mark Shenin, N Dinesh Reddy, Matthew O'Toole, and Srinivasa Narasimhan
In European Conference on Computer Vision (ECCV) 2020 (ORAL)
[PDF] [Project Page] [Supp] [Video] [Video Long] [BibTex]
2019
Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks
N Dinesh Reddy, Minh Vo, and Srinivasa Narasimhan
In International Conference on Computer vision and pattern recognition (CVPR) 2019
[PDF] [Poster] [Supp] [Dataset] [Project Page] [BibTex] [Code]
2018
CarFusion: Combining Part Detection and Point Tracking for Dynamic 3D Reconstruction of Vehicles
N Dinesh Reddy, Minh Vo, and Srinivasa Narasimhan
In International Conference on Computer vision and pattern recognition (CVPR) 2018
[PDF] [Poster] [Dataset] [Supp] [Project Page] [Video] [BibTex]
LSD-NET: Look, Step and Detect for joint Navigation and Multi-View Recognition with Deep Reinforcement Learning
N Dinesh Reddy
In arxiv 2018
[PDF]
2017
Temporal Semantic Motion Segmentation using Spatio Temporal Optimization
Nazrul Athar, N Dinesh Reddy and K Madhava Krishna
In International Conference on Energy Minimization Methods in Computer Vision and Pattern
Recognition (EMMCVPR) 2017 (ORAL)
[PDF] [Dataset] [BibTex]
Joint Semantic and Motion Segmentation for Dynamic Scenes using Deep Convolutional Networks
Nazrul Athar, N Dinesh Reddy and K Madhava Krishna
In International Conference on Computer Vision Theory and Applications (VISAPP) 2017
[PDF] [Project Page] [Video] [Dataset] [BibTex]
2016
Incremental Real-Time Multibody VSLAM with Trajectory Optimization Using Stereo Camera
N Dinesh Reddy, Iman Abbasnejad,A Sheetal Reddy, Amit K Mondal and Vindhya Devalla
In IEEE International Conference on Intelligent Robots and Systems (IROS) 2016
[PDF] [BibTex]
Monocular Reconstruction of Vehicles: Combining SLAM with Shape Priors
Falak Chayya, N Dinesh Reddy,Sarthak Upadhyay, Visesh Chari, Zeeshan Zia and K Madhava Krishna
In IEEE International Conference on Robotics and Automation (ICRA) 2016
[PDF] [Project Page] [Video] [BibTex]
2015
Dynamic Body VSLAM with Semantic Constraints
N Dinesh Reddy,Prateek Singhal, Visesh Chari and K Madhava Krishna
In IEEE International Conference on Intelligent Robots and Systems (IROS) 2015
[PDF] [Project Page] [Dataset] [Video] [BibTex]
2014
Semantic Motion segmentation using Dense CRF
N Dinesh Reddy,Prateek Singhal and K Madhava Krishna
In Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) 2014 (ORAL)
[PDF] [Project Page] [Dataset] [Video] [BibTex]
Traveled Locations
