{"title":"Optical Flow for Rigid Multi-Motion Scenes","authors":"Tomas Gerlich, Jakob Eriksson","doi":"10.1109/3DV.2016.30","DOIUrl":"https://doi.org/10.1109/3DV.2016.30","url":null,"abstract":"We observe that in many applications, the motion present in a scene is well characterized by a small number of (rigid) motion hypotheses. Based on this observation, we present rigid multi-motion optical flow (RMM). By restricting flow to one of several motion hypotheses, RMM produces more accurate optical flow than arbitrary motion models. We evaluate an algorithm based on RMM on a novel synthetic dataset, consisting of 12 photo-realistically rendered scenes containing rigid vehicular motion and a corresponding, exact, ground truth. On this dataset, we demonstrate a substantial advantage of RMM over general-purpose algorithms: going from 36% outliers with the DiscreteFlow algorithm, to 26% with ours, with a mean error reduction from 8.4px to 6.9px. We also perform qualitative evaluation on real-world imagery from traffic cameras.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132316697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Learning a General-Purpose Confidence Measure Based on O(1) Features and a Smarter Aggregation Strategy for Semi Global Matching","authors":"Matteo Poggi, S. Mattoccia","doi":"10.1109/3DV.2016.61","DOIUrl":"https://doi.org/10.1109/3DV.2016.61","url":null,"abstract":"Inferring dense depth from stereo is crucial for several computer vision applications and Semi Global Matching (SGM) is often the preferred choice due to its good tradeoff between accuracy and computation requirements. Nevertheless, it suffers of two major issues: streaking artifacts caused by the Scanline Optimization (SO) approach, at the core of this algorithm, may lead to inaccurate results and the high memory footprint that may become prohibitive with high resolution images or devices with constrained resources. In this paper, we propose a smart scanline aggregation approach for SGM aimed at dealing with both issues. In particular, the contribution of this paper is threefold: i) leveraging on machine learning, proposes a novel generalpurpose confidence measure suited for any for stereo algorithm, based on O(1) features, that outperforms state of-the-art ii) taking advantage of this confidence measure proposes a smart aggregation strategy for SGM enabling significant improvements with a very small overhead iii) the overall strategy drastically reduces the memory footprint of SGM and, at the same time, improves its effectiveness and execution time. We provide extensive experimental results, including a cross-validation with multiple datasets (KITTI 2012, KITTI 2015 and Middlebury 2014).","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132419881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chen Kong, Rui Zhu, Hamed Kiani Galoogahi, S. Lucey
{"title":"Structure from Category: A Generic and Prior-Less Approach","authors":"Chen Kong, Rui Zhu, Hamed Kiani Galoogahi, S. Lucey","doi":"10.1109/3DV.2016.38","DOIUrl":"https://doi.org/10.1109/3DV.2016.38","url":null,"abstract":"Inferring the motion and shape of non-rigid objects from images has been widely explored by Non-Rigid Structure from Motion (NRSfM) algorithms. Despite their promising results, they often utilize additional constraints about the camera motion (e.g. temporal order) and the deformation of the object of interest, which are not always provided in real-world scenarios. This makes the application of NRSfM limited to very few deformable objects (e.g. human face and body). In this paper, we propose the concept of Structure from Category (SfC) to reconstruct 3D structure of generic objects solely from images with no shape and motion constraint (i.e. prior-less). Similar to the NRSfM approaches, SfC involves two steps: (i) correspondence, and (ii) inversion. Correspondence determines the location of key points across images of the same object category. Once established, the inverse problem of recovering the 3D structure from the 2D points is solved over an augmented sparse shape-space model. We validate our approach experimentally by reconstructing 3D structures of both synthetic and natural images, and demonstrate the superiority of our approach to the state-of-the-art low-rank NRSfM approaches.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134160425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jihua Zhu, Di Wang, Xiuxiu Bai, Huimin Lu, Congcong Jin, Zhongyu Li
{"title":"Registration of Point Clouds Based on the Ratio of Bidirectional Distances","authors":"Jihua Zhu, Di Wang, Xiuxiu Bai, Huimin Lu, Congcong Jin, Zhongyu Li","doi":"10.1109/3DV.2016.85","DOIUrl":"https://doi.org/10.1109/3DV.2016.85","url":null,"abstract":"Despite the fact that original Iterative Closest Point(ICP) algorithm has been widely used for registration, itcannot tackle the problem when two point clouds are par-tially overlapping. Accordingly, this paper proposes a ro-bust approach for the registration of partially overlappingpoint clouds. Given two initially posed clouds, it firstlybuilds up bilateral correspondence and computes bidirec-tional distances for each point in the data shape. Based onthe ratio of bidirectional distances, the exponential functionis selected and utilized to calculate the probability value,which can indicate whether the point pair belongs to theoverlapping part or not. Subsequently, the probability val-ue can be embedded into the least square function for reg-istration of partially overlapping point clouds and a novelvariant of ICP algorithm is presented to obtain the optimalrigid transformation. The proposed approach can achievegood registration of point clouds, even when their overlappercentage is low. Experimental results tested on public da-ta sets illustrate its superiority over previous approaches onrobustness.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115105106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rodrigo Ortiz Cayon, Abdelaziz Djelouah, Francisco Massa, Mathieu Aubry, G. Drettakis
{"title":"Automatic 3D Car Model Alignment for Mixed Image-Based Rendering","authors":"Rodrigo Ortiz Cayon, Abdelaziz Djelouah, Francisco Massa, Mathieu Aubry, G. Drettakis","doi":"10.1109/3DV.2016.37","DOIUrl":"https://doi.org/10.1109/3DV.2016.37","url":null,"abstract":"Image-Based Rendering (IBR) allows good-quality free-viewpoint navigation in urban scenes, but suffers from artifacts on poorly reconstructed objects, e.g., reflective surfaces such as cars. To alleviate this problem, we propose a method that automatically identifies stock 3D models, aligns them in the 3D scene and performs morphing to better capture image contours. We do this by first adapting learning-based methods to detect and identify an object class/pose in images. We then propose a method which exploits all available information, namely partial and inaccurate 3D reconstruction, multi-view calibration, image contours and the 3D model to achieve accurate object alignment suitable for subsequent morphing. These steps provide models which are well-aligned in 3D and to contours in all the images of the multi-view dataset, allowing us to use the resulting model in our mixed IBR algorithm. Our results show significant improvement in image quality for free-viewpoint IBR, especially when moving far from the captured viewpoints.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128613110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robust Feature-Preserving Denoising of 3D Point Clouds","authors":"Sk. Mohammadul Haque, V. Govindu","doi":"10.1109/3DV.2016.17","DOIUrl":"https://doi.org/10.1109/3DV.2016.17","url":null,"abstract":"The increased availability of point cloud data in recent years has lead to a concomitant requirement for high quality denoising methods. This is particularly the case with data obtained using depth cameras or from multi-view stereo reconstruction as both approaches result in noisy point clouds and include significant outliers. Most of the available denoising methods in the literature are not sufficiently robust to outliers and/or are unable to preserve fine-scale 3D features in the denoised representations. In this paper we propose an approach to point cloud denoising that is both robust to outliers and capable of preserving fine-scale 3D features. We identify and remove outliers by utilising a dissimilarity measure based on point positions and their corresponding normals. Subsequently, we use a robust approach to estimate surface point positions in a manner designed to preserve sharp and fine-scale 3D features. We demonstrate the efficacy of our approach and compare with similar methods in the literature by means of experiments on synthetic and real data including large-scale 3D reconstructions of heritage monuments.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129082655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Absolute Pose and Structure from Motion for Surfaces of Revolution: Minimal Problems Using Apparent Contours","authors":"Cody J. Phillips, Kostas Daniilidis","doi":"10.1109/3DV.2016.86","DOIUrl":"https://doi.org/10.1109/3DV.2016.86","url":null,"abstract":"The class of objects that can be represented by surfaces of revolution (SoRs) is highly prevalent in human work and living spaces. Due to their prevalence and convenient geometric properties, SoRs have been employed over the past thirty years for single-view camera calibration and pose estimation, and have been studied in terms of SoR object reconstruction and recognition. Such treatment has provided techniques for the automatic identification and classification of important SoR structures, such as apparent contours, cross sections, bitangent points, creases, and inflections. The presence of these structures are crucial to most SoR-based image metrology algorithms. This paper develops single-view and two-view pose recovery and reconstruction formulations that only require apparent contours, and no other SoR features.The primary objective of this paper is to present and experimentallyvalidate the minimal problems pertaining toSoR metrology from apparent contours. For a single view with a known reference model, this includes absolute pose recovery. For many views and no reference model this is extended to structure from motion (SfM). Assuming apparent contours as input that have been identified and segmented with reasonable accuracy, the minimal problems aredemonstrated to produce accurate SoR pose and shape results when used as part of a RANSAC-based hypothesis generation and evaluation pipeline.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130826788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Thonat, Eli Shechtman, Sylvain Paris, G. Drettakis
{"title":"Multi-View Inpainting for Image-Based Scene Editing and Rendering","authors":"T. Thonat, Eli Shechtman, Sylvain Paris, G. Drettakis","doi":"10.1109/3DV.2016.44","DOIUrl":"https://doi.org/10.1109/3DV.2016.44","url":null,"abstract":"We propose a method to remove objects such as people and cars from multi-view urban image datasets, enabling free-viewpoint IBR in the edited scenes. Our method combines information from multi-view 3D reconstruction with image inpainting techniques, by formulating the problem as an optimization of a global patch-based objective function. We use Image-Based Rendering (IBR) techniques to reproject information from neighboring views, and 3D multi-view stereo reconstruction to perform multiview coherent initialization for inpainting of pixels not filled by reprojection. Our algorithm performs multi-view consistent inpainting for color and 3D by blending reprojections with patch-based image inpainting. We run our algorithm on casually captured datasets, and Google StreetViewdata, removing objects cars, people and pillars, showing that our approach produces results of sufficient quality for free-viewpoint IBR on \"cleaned up\" scenes, as well as IBR scene editing, such as limited motion of real objects.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115284977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fabio Maninchedda, Christian Häne, Martin R. Oswald, M. Pollefeys
{"title":"Face Reconstruction on Mobile Devices Using a Height Map Shape Model and Fast Regularization","authors":"Fabio Maninchedda, Christian Häne, Martin R. Oswald, M. Pollefeys","doi":"10.1109/3DV.2016.59","DOIUrl":"https://doi.org/10.1109/3DV.2016.59","url":null,"abstract":"We present a system which is able to reconstruct human faces on mobile devices with only on-device processing using the sensors which are typically built into a current commodity smart phone. Such technology can for example be used for facial authentication purposes or as a fast preview for further post-processing. Our method uses recently proposed techniques which compute depth maps by passive multi-view stereo directly on the device. We propose an efficient method which recovers the geometry of the face from the typically noisy point cloud. First, we show that we can safely restrict the reconstruction to a 2.5D height map representation. Therefore we then propose a novel low dimensional height map shape model for faces which can be fitted to the input data efficiently even on a mobile phone. In order to be able to represent instance specific shape details, such as moles, we augment the reconstruction from the shape model with a distance map which can be regularized efficiently. We thoroughly evaluate our approach on synthetic and real data, thereby we use both high resolution depth data acquired using high quality multi-view stereo and depth data directly computed on mobile phones.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124931951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fast Obstacle Detection Using Sparse Edge-Based Disparity Maps","authors":"Dexmont Alejandro Peãa Carrillo, Alistair Sutherland","doi":"10.1109/3DV.2016.80","DOIUrl":"https://doi.org/10.1109/3DV.2016.80","url":null,"abstract":"This paper presents a fast approach for computing image stixels from a sparse edge-based disparity map. The use of edge-based disparity maps speeds up the computation of the stixels as only a few pixels must be processed compared to approaches which use dense disparity maps. The proposed approach produces as output the stixels in one of the views of the stereo-pair and a segmentation of the edge-points into obstacle. Additionally the proposed approach allows the identification of partially occluded objects by allowing more than one stixel per image column. The proposed approach is fast to compute with no loss on accuracy.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121507380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}