Datasets



CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images

This dataset contains CoarseData and FineData augmented from 3131 images of 300-W with the method described in the paper 3DFaceNet: Real-time Dense Face Reconstruction via Synthesizing Photo-realistic Face Images. CoarseData is constructed by varying poses and expressions of the original images. FineData is constructed by transferring details from other images to the original images. We augment each image 30 times for both CoarseData and FineData.

guo_facedata

Download: Training data



Alive Caricature from 2D to 3D

This repository contain the caricature images with corresponding landmark in paper: Alive Caricature from 2D to 3D. The Caricature_w_landmark folder contains the caricature images with its landmarks. We named them by number. e.g. 1.jpg with its landmarks file named 1.txt.

alive

Download: Training data



Structure Completion for Facade Layouts

Test data for the paper "Structure Completion for Facade Layouts".

feature_aligned_xu

Download: Structure Completion for Facade Layouts



Multi-Scale Partial Intrinsic Symmetry Detection

Test data for the paper "Multi-Scale Partial Intrinsic Symmetry Detection.

feature_aligned_xu

Download: Multi-Scale Partial Intrinsic Symmetry Detection



Animated Construction of Line Drawings

Test data for the paper "Animated Construction of Line Drawings.

feature_aligned_xu

Download: Animated Construction of Line Drawings



Projective Feature Learning for 3D Shapes with Multi-View Depth Images

Test data for the paper "Projective Feature Learning for 3D Shapes with Multi-View Depth Images.

feature_aligned_xu

Download: Projective Feature Learning for 3D Shapes with Multi-View Depth Images



Spherical parameterizations of 5181 genus zero meshes

We provide 5181 meshes and their spherical parameterizations on Dropbox.

sel_sp

Download: Spherical parameterizations data



Data Set for Parameterizations

This large testing benchmark contains 20712 meshes. It starts from well cut meshes D1, continues with moderately bad ones D2, and ends with extremely challenging examples D3. If you use our data set, please cite [Liu et al. 2018] and [Chai et al. 2018].

D1_show

Download: Planar parameterizations data



Data Set for PolyCube-Map

Data Set containts 106 models which vary from natrual objects to CAD models. It is mainly based on the benchmark of global seamless parameterization and mesh segmentation.

selected_polycube

Download: PolyCube-Map data