Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction

Takuma Doi, Fumio Okura, Toshiki Nagahara, Yasuyuki Matsushita, Yasushi Yagi; Proceedings of the Asian Conference on Computer Vision (ACCV), 2020

Abstract


This paper proposes a multi-view extension of instance segmentation without relying on texture or shape descriptor matching. Multi-view instance segmentation becomes challenging for scenes with repetitive textures and shapes, e.g., plant leaves, due to the difficulty of multi-view matching using texture or shape descriptors. To this end, we propose a multi-view region matching method based on epipolar geometry, which does not rely on any feature descriptors. We further show that the epipolar region matching can be easily integrated into instance segmentation and effective for instance-wise 3D reconstruction. Experiments demonstrate the improved accuracy of multi-view instance matching and the 3D reconstruction compared to the baseline methods.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Doi_2020_ACCV, author = {Doi, Takuma and Okura, Fumio and Nagahara, Toshiki and Matsushita, Yasuyuki and Yagi, Yasushi}, title = {Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {November}, year = {2020} }