The Second Workshop on 3D Reconstruction Meets Semantics: Challenge Results Discussion

This paper discusses a reconstruction challenge held as a part of the second 3D Reconstruction meets Semantics workshop (3DRMS). The challenge goals and datasets are introduced, including both synthetic and real data from outdoor scenes, here represented by gardens with a variety of bushes, trees, other plants and objects. Both qualitative and quantitative evaluation of the challenge participants’ submissions is given in categories of geometric and semantic accuracy. Finally, comparison of submitted results with baseline methods is given, showing a modest performance increase in some of the categories.

[1]  Theo Gevers,et al.  Joint Learning of Intrinsic Images and Semantic Segmentation , 2018, ECCV.

[2]  Andreas Geiger,et al.  Efficient Large-Scale Stereo Matching , 2010, ACCV.

[3]  Alexandre Boulch,et al.  Technical Report: Co-learning of geometry and semantics for online 3D mapping , 2019, ArXiv.

[4]  Roland Siegwart,et al.  Unified temporal and spatial calibration for multi-sensor systems , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Michael M. Kazhdan,et al.  Screened poisson surface reconstruction , 2013, TOGS.

[6]  Torsten Sattler,et al.  A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Theo Gevers,et al.  Three for one and one for three: Flow, Segmentation, and Surface Normals , 2018, BMVC.

[8]  Marc Pollefeys,et al.  Dense Semantic 3D Reconstruction , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Marc Pollefeys,et al.  Learning Priors for Semantic 3D Reconstruction , 2018, ECCV.

[10]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[12]  Daniel Cremers,et al.  FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture , 2016, ACCV.

[13]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Robert B. Fisher,et al.  Consistent Semantic Annotation of Outdoor Datasets via 2D/3D Label Transfer , 2018, Sensors.

[15]  Jan-Michael Frahm,et al.  Structure-from-Motion Revisited , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jan-Michael Frahm,et al.  Pixelwise View Selection for Unstructured Multi-View Stereo , 2016, ECCV.

[17]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[18]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).