Krishna Murthy1, Sai Krishna Gottipati2, Falak Chhaya3, Madhava Krishna4
11:30 - 12:45 | Tue 30 May | Room 4311/4312 | TUB3
We present an approach for reconstructing vehicles from a single (RGB) image, in the context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to an image can be used to reason about the reverse process, i.e., how shapes (back-)project from 2D to 3D. We encode this knowledge in shape priors, which are learnt over a small keypoint-annotated dataset. We then formulate a shape-aware adjustment problem that uses the learnt shape priors to recover the 3D pose and shape of a query object from an image. For shape representation and inference, we leverage recent successes of Convolutional Neural Networks (CNNs) for the task of object and keypoint detection, and train a novel cascaded fully-convolutional architecture to detect vehicle keypoints in images. The shape-aware adjustment then robustly recovers shape (3D locations of the detected keypoints) while simultaneously filling in occluded keypoints. To tackle estimation errors incurred due to erroneously detected keypoints, we use an Iteratively Re-weighted Least Squares (IRLS) scheme to robustify the optimization, and as a by-product characterize noise models for each predeicted keypoint. We evaluate our approach on autonomous driving benchmarks, and present superior results to existing monocular approaches.
No information added