# CAE-ELM
## Introduction
3D shape features play a crucial role in graphics applications, such as 3D shape matching, recognition, and retrieval. Various 3D shape descriptors have been developed over the last two decades; however, existing descriptors are handcrafted features that are labor-intensively designed and cannot extract discriminative information for a large set of data.
We propose a rapid 3D feature learning method, namely, a convolutional auto-encoder extreme learning machine (CAE-ELM) that combines the advantages of the convolutional neuron network, auto-encoder, and extreme learning machine (ELM). This method performs better and faster than other methods.
In addition, we define a novel architecture based on CAE-ELM. The architecture accepts two types of 3D shape representation, namely, voxel data and signed distance field data (SDF), as inputs to extract the global and local features of 3D shapes. Voxel data describe structural information, whereas SDF data contain details on 3D shapes.
Moreover, the proposed CAE-ELM can be used in practical graphics applications, such as 3D shape completion. Experiments show that the features extracted by CAE-ELM are superior to existing hand-crafted features and other deep learning methods or ELM models.
## Results
The classification accuracy of the proposed architecture is superior to that of other methods on ModelNet10 (91.4%) and ModelNet40 (84.35%). The training process also runs faster than existing deep learning methods by approximately two orders of magnitude.
## run
Convert your 3D shape into 2 types: voxel and sdf data.
If you only have *.off files or dirs, you can copy ./readdata/getsdfdata/* and ./readdata/getvoxeldata/* to your off dirs, then run the "runexe.m" to generate voxel data and sdf data.
After that, you can copy the sdfdata.mat and voxeldata.mat to ./data, and add the path in "run_fea_combine.m". Then run "run_fea_combine.m".
没有合适的资源?快使用搜索试试~ 我知道了~
CAE-ELM:卷积自动编码器极限学习机
共33个文件
m:27个
md:1个
c:1个
需积分: 48 14 下载量 79 浏览量
2021-04-29
18:29:51
上传
评论 5
收藏 53KB ZIP 举报
温馨提示
CAE-ELM 介绍 3D形状特征在图形应用程序中起着至关重要的作用,例如3D形状匹配,识别和检索。 在过去的二十年中,已经开发出了各种3D形状描述符。 但是,现有的描述符是手工设计的功能,需要大量劳动来设计,并且无法为大量数据提取判别信息。 我们提出了一种快速的3D特征学习方法,即卷积自动编码器极限学习机(CAE-ELM),该方法结合了卷积神经元网络,自动编码器和极限学习机(ELM)的优势。 此方法比其他方法执行得更好,更快。 另外,我们定义了一种基于CAE-ELM的新颖架构。 该体系结构接受两种类型的3D形状表示,即体素数据和有符号距离场数据(SDF),作为提取3D形状的全局和局部特征的输入。 体素数据描述结构信息,而SDF数据包含3D形状的详细信息。 此外,提出的CAE-ELM可以用于实际的图形应用程序,例如3D形状完成。 实验表明,CAE-ELM提取的特征优于现有的手工特征以
资源推荐
资源详情
资源评论
收起资源包目录
CAE-ELM-master.zip (33个子文件)
CAE-ELM-master
Actfunc.m 831B
CAE_ELM.m 7KB
getPooledFeature.m 474B
getAEFeature.m 524B
AE_train.m 2KB
CAE_ff.m 756B
poolLayer.m 2KB
convLayer.m 958B
getConvFeature.m 879B
procrustNew.m 859B
run_fea_combine.m 1KB
util
show3D.m 1KB
show_sample.m 980B
showVoxel.m 207B
CAE_getH.m 2KB
CAE_ELM_voxel.m 5KB
readdata
getvoxeldata
polygon2voxel_double.mexa64 10KB
polygon2voxel.m 6KB
eat_comments.m 658B
polygon2voxel_double.mexw64 11KB
runexe.m 3KB
polygon2voxel_double.c 6KB
readOFF.m 3KB
getsdfdata
SDFGen.exe 43KB
runexe.m 137B
getdata.m 3KB
run.m 16B
README.md 2KB
AE_ff.m 457B
CAE_ELM_combine.m 5KB
getInput.m 626B
README.md.bak 2KB
combine_Harray.m 276B
共 33 条
- 1
资源评论
潜水小透明
- 粉丝: 33
- 资源: 4508
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功