PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationMonocular Depth EstimationPose EstimationSimilar Papers 제목 키워드 기반
When OT meets MoM: Robust estimation of Wasserstein Distance
Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of efficient approximations. In this work, we …
Generative Adversarial NetworkWasserstein Weisfeiler-Lehman Subtree Distance for Graph-Structured Data
Defining a valid graph distance is a challenging task in graph machine learning because we need to consider the theoretical validity of the distance, its computational complexity, and effectiveness as a distance between …
Graph ClassificationvalidA New Robust Partial $p$-Wasserstein-Based Metric for Comparing Distributions
The $2$-Wasserstein distance is sensitive to minor geometric differences between distributions, making it a very powerful dissimilarity metric. However, due to this sensitivity, a small outlier mass can also cause a sign…
Image RetrievalSensitivityConvergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
Optimal Transport has sparked vivid interest in recent years, in particular thanks to the Wasserstein distance, which provides a geometrically sensible and intuitive way of comparing probability measures. For computation…
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasse…
object-detectionObject DetectionObject Detection In Aerial Imagesregression+1