297 citations · 1.1k across the 40 of their papers we have counts for
11 papers · 1 filter
Self-Supervised 3D Keypoint Learning for Ego-motion Estimation
Jiexiong Tang, Rares Ambrus, Vitor Guizilini +4
Detecting and matching robust viewpoint-invariant keypoints is critical for visual SLAM and Structure-from-Motion. State-of-the-art learning-based methods generate training samples…
Real-Time Panoptic Segmentation from Dense Detections
Rui Hou, Jie Li, Arjun Bhargava +5
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot…
Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances
Vitor Guizilini, Jie Li, Rares Ambrus +2
Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression…
Two Stream Networks for Self-Supervised Ego-Motion Estimation
Rares Ambrus, Vitor Guizilini, Jie Li +2
Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appe…
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
Sergey Zakharov, Wadim Kehl, Arjun Bhargava +1
We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an…
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
Karttikeya Mangalam, Ehsan Adeli, Kuan-Hui Lee +2
We tackle the problem of Human Locomotion Forecasting, a task for jointly predicting the spatial positions of several keypoints on the human body in the near future under an egocen…