paper-with-me

홈 › Papers

PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation

2020-06-03 · Noriaki Hirose, Satoshi Koide, Keisuke Kawano, Ruho Kondo

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.

📄 PDF Abstract BibTeX arXiv:2006.02068

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationMonocular Depth EstimationPose Estimation

Similar Papers 제목 키워드 기반

When OT meets MoM: Robust estimation of Wasserstein Distance

2020-06-18 · Guillaume Staerman, Pierre Laforgue, Pavlo Mozharovskyi, Florence d'Alché-Buc

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 Network

Wasserstein Weisfeiler-Lehman Subtree Distance for Graph-Structured Data

2021-09-29 · Zhongxi Fang, Jianming Huang, Hiroyuki Kasai

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 Classificationvalid

A New Robust Partial $p$-Wasserstein-Based Metric for Comparing Distributions

2024-05-06 · Sharath Raghvendra, Pouyan Shirzadian, Kaiyi Zhang

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 RetrievalSensitivity

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses

2023-07-21 · Eloi Tanguy

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

2021-01-28 · Xue Yang, Junchi Yan, Qi Ming, Wentao Wang 외

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