3D Pose Regression using Convolutional Neural Networks
This addresses 3D pose estimation for computer vision tasks like autonomous navigation, but appears incremental as it modifies existing CNN approaches.
The paper tackled 3D pose estimation by proposing a CNN regression framework instead of classification, arguing the pose space is continuous, and achieved competitive performance on PASCAL3D+.
3D pose estimation is a key component of many important computer vision tasks such as autonomous navigation and 3D scene understanding. Most state-of-the-art approaches to 3D pose estimation solve this problem as a pose-classification problem in which the pose space is discretized into bins and a CNN classifier is used to predict a pose bin. We argue that the 3D pose space is continuous and propose to solve the pose estimation problem in a CNN regression framework with a suitable representation, data augmentation and loss function that captures the geometry of the pose space. Experiments on PASCAL3D+ show that the proposed 3D pose regression approach achieves competitive performance compared to the state-of-the-art.