G2MF-WA:Geometric multi-model fitting with weakly annotated data  

作　　者：Chao Zhang Xuequan Lu Katsuya Hotta Xi Yang 

机构地区：[1]University of Fukui,Fukui,910-8507,Japan [2]Deakin University,Waurn Ponds,3216,Australia [3]The University of Tokyo,Tokyo,113-8656,Japan

出　　处：《Computational Visual Media》2020年第2期135-145,共11页计算可视媒体（英文版）

基　　金：supported in part by JSPS KAKENHI Grant JP18K17823;supported in part by Deakin CY01-251301-F003-PJ03906-PG00447。

摘　　要：In this paper we address the problem of geometric multi-model fitting using a few weakly annotated data points,which has been little studied so far.In weak annotating(WA),most manual annotations are supposed to be correct yet inevitably mixed with incorrect ones.Such WA data can naturally arise through interaction in various tasks.For example,in the case of homography estimation,one can easily annotate points on the same plane or object with a single label by observing the image.Motivated by this,we propose a novel method to make full use of WA data to boost multi-model fitting performance.Specifically,a graph for model proposal sampling is first constructed using the WA data,given the prior that WA data annotated with the same weak label has a high probability of belonging to the same model.By incorporating this prior knowledge into the calculation of edge probabilities,vertices(i.e.,data points)lying on or near the latent model are likely to be associated and further form a subset or cluster for effective proposal generation.Having generated proposals,α-expansion is used for labeling,and our method in return updates the proposals.This procedure works in an iterative way.Extensive experiments validate our method and show that it produces noticeably better results than state-of-the-art techniques in most cases.

关 键 词：geometric multi-model fitting weak annotation multi-homography detection two-view motion segmentation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]