A Structure-Aware Method for Direct Pose Estimation
This work provides an improved direct method for camera pose estimation, which is beneficial for applications requiring deterministic and constant-time pose regression.
This paper addresses the problem of estimating camera pose from a single image using a direct method. The proposed approach integrates explicit 3D constraints into the network, resulting in significantly lower error compared to existing direct methods.
Estimating camera pose from a single image is a fundamental problem in computer vision. Existing methods for solving this task fall into two distinct categories, which we refer to as direct and indirect. Direct methods, such as PoseNet, regress pose from the image as a fixed function, for example using a feed-forward convolutional network. Such methods are desirable because they are deterministic and run in constant time. Indirect methods for pose regression are often non-deterministic, with various external dependencies such as image retrieval and hypothesis sampling. We propose a direct method that takes inspiration from structure-based approaches to incorporate explicit 3D constraints into the network. Our approach maintains the desirable qualities of other direct methods while achieving much lower error in general.