PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation
This addresses the challenge of accurate 3D reconstruction from single images for applications like autonomous driving, though it is incremental as it builds on existing state-of-the-art methods.
The paper tackles the problem of geometric inconsistencies in monocular depth and pose estimation by proposing a novel objective using Wasserstein distance between point clouds, resulting in improved accuracy on the KITTI dataset.
We propose a novel objective for penalizing geometric inconsistencies to improve the depth and pose estimation performance of monocular camera images. Our objective is designed using the Wasserstein distance between two point clouds, estimated from images with different camera poses. The Wasserstein distance can impose a soft and symmetric coupling between two point clouds, which suitably maintains geometric constraints and results in a differentiable objective. By adding our objective to the those of other state-of-the-art methods, we can effectively penalize geometric inconsistencies and obtain highly accurate depth and pose estimations. Our proposed method is evaluated using the KITTI dataset.