Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

By Li Yi, Lin Shao, Manolis Savva, Haibin Huang, Yang Zhou, Qirui Wang, Benjamin Graham, Martin Engelcke, Roman Klokov, Victor S. Lempitsky and 40 more. 2017

70 citations recorded by the source corpus.

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, methodology): “CD has been used in recent shape retrieval challenges [67].”
PointCNN: Convolution On X-Transformed Points (2018, methodology): “Note that the part averaged IoU metric for ShapeNet Parts is the one used in [56].”
Image Segmentation Using Deep Learning: A Survey (2020, methodology): “ShapeNet Core: ShapeNetCore is a subset of the full ShapeNet dataset [158] with single clean 3D models and manually verified category and alignment annotations [159].”
Synthetic Data for Deep Learning (2019, methodology): “ShapeNetCore 2017 [672] 51K manually verified models from 55 categories”
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks (2017, methodology): “To evaluate the accuracy of our models, we adopt the intersection-over-union (IoU) metric of [23].”
Recurrent Slice Networks for 3D Segmentation of Point Clouds (2018, methodology): “Benjamin Graham designed a sparse convolution network [5, 6] and applied it for 3D segmentation tasks [36].”
What Do Single-View 3D Reconstruction Networks Learn? (2019, methodology): “Unlike several recent approaches, which evaluated only on the 13 largest classes, we deliberately use all 55 classes, as was done in [56].”