2 code implementations • 27 Mar 2022 • Jinkun Cao, Xinshuo Weng, Rawal Khirodkar, Jiangmiao Pang, Kris Kitani
Multi-Object Tracking (MOT) has rapidly progressed with the development of object detection and re-identification.
Ranked #1 on
Multiple Object Tracking
on KITTI Tracking test
no code implementations • 24 Mar 2022 • Rawal Khirodkar, Shashank Tripathi, Kris Kitani
Along with the input image, we condition the top-down model on spatial context from the image in the form of body-center heatmaps.
Ranked #16 on
3D Human Pose Estimation
on 3DPW
(using extra training data)
1 code implementation • ICCV 2021 • Shun Iwase, Xingyu Liu, Rawal Khirodkar, Rio Yokota, Kris M. Kitani
Furthermore, we utilize differentiable Levenberg-Marquardt (LM) optimization to refine a pose fast and accurately by minimizing the feature-metric error between the input and rendered image representations without the need of zooming in.
Ranked #3 on
6D Pose Estimation using RGB
on LineMOD
1 code implementation • ICCV 2021 • Rawal Khirodkar, Visesh Chari, Amit Agrawal, Ambrish Tyagi
Specifically, we achieve 70. 0 AP on CrowdPose and 42. 5 AP on OCHuman test sets, a significant improvement of 2. 4 AP and 6. 5 AP over the prior art, respectively.
Ranked #1 on
Pose Estimation
on OCHuman
no code implementations • 3 Dec 2018 • Rawal Khirodkar, Kris M. Kitani
Domain Randomization (DR) is known to require a significant amount of training data for good performance.
1 code implementation • 14 Nov 2018 • Rawal Khirodkar, Donghyun Yoo, Kris M. Kitani
We address the issue of domain gap when making use of synthetic data to train a scene-specific object detector and pose estimator.