Towards Learning Monocular 3D Object Localization From 2D Labels using the Physical Laws of Motion
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead of using 3D labels, our model is trained with easy-to-annotate 2D labels along with the physical knowledge of the object's motion. Given this information, the model can infer the latent third dimension, even though it has never seen this information during training. Our method is evaluated on both synthetic and real-world datasets, and we are able to achieve a mean distance error of just 6 cm in our experiments on real data. The results indicate the method's potential as a step towards learning 3D object location estimation, where collecting 3D data for training is not feasible.
Code (1)
Tasks
Monocular 3D Object LocalizationObjectObject LocalizationSimilar Papers 제목 키워드 기반
Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach
Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single m…
3D ReconstructionRobot NavigationKinematic 3D Object Detection in Monocular Video
Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not b…
3D Object DetectionMonocular 3D Object DetectionObjectobject-detection+2Object-Aware Centroid Voting for Monocular 3D Object Detection
Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera. However, recent approaches either rely on expensive LiDAR devices, or resort to dense pixel-wise depth estimation that cau…
3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+3Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection
Monocular 3D object detection continues to attract attention due to the cost benefits and wider availability of RGB cameras. Despite the recent advances and the ability to acquire data at scale, annotation cost and compl…
3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+2Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop a…
3D Object DetectionAutonomous DrivingDepth EstimationMonocular Depth Estimation+3