DeepAI
Log In Sign Up

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

10/17/2017
by   Li Yi, et al.
0

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.

READ FULL TEXT
04/12/2018

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

We study 3D shape modeling from a single image and make contributions to...
06/16/2022

Use of Kernel Density Estimation to understand the spatial trends of attacking possessions in rugby league

Despite having the potential to provide significant insights into tactic...
03/21/2019

SkelNetOn 2019 Dataset and Challenge on Deep Learning for Geometric Shape Understanding

We present SkelNetOn 2019 Challenge and Deep Learning for Geometric Shap...
12/04/2018

Learning Single-View 3D Reconstruction with Adversarial Training

Single-view 3D shape reconstruction is an important but challenging prob...
06/15/2019

Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

3D reconstruction is a longstanding ill-posed problem, which has been ex...
01/24/2020

VerSe: A Vertebrae Labelling and Segmentation Benchmark

In this paper we report the challenge set-up and results of the Large Sc...
01/04/2021

Stereo Correspondence and Reconstruction of Endoscopic Data Challenge

The stereo correspondence and reconstruction of endoscopic data sub-chal...