単一画像からの車両3D形状復元：道路シーン理解のための形状事前分布
Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding
単眼RGB画像から車両の3D姿勢と形状を復元するため、キーポイント注釈データで学習した形状事前分布とCNNによるキーポイント検出を組み合わせた手法を提案。遮蔽にも頑健で、既存の単眼・ステレオ手法を上回る精度を示した。
著者: J. Krishna Murthy, G. V. Sai Krishna, Falak Chhaya, K. Madhava Krishna
分類: cs.CV, cs.RO
原文アブストラクト
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 \emph{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 localization, and train a novel cascaded fully-convolutional architecture to localize vehicle \emph{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 for robust optimization, and as a by-product characterize noise models for each predicted keypoint. We evaluate our approach on autonomous driving benchmarks, and present superior results to existing monocular, as well as stereo approaches.
