litlas
Log inCreate account

ShapeNet: An Information-Rich 3D Model Repository

Authors: Angel X. Chang, Thomas A. Funkhouser, Leonidas J. Guibas, Pat Hanrahan, Qi-Xing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, Fisher Yu - http://vision.cs.princeton.edu/projects/2015/ShapeNet/paper.pdf 2023 cited by 3,963

We present ShapeNet: a richly-annotated, large-scale repository of shapes represented by 3D CAD models of objects. ShapeNet contains 3D models from a multitude of semantic categories and organizes them under the WordNet taxonomy. It is a collection of datasets providing many semantic annotations for each 3D model such as consistent rigid alignments, parts and bilateral symmetry planes, physical sizes, keywords, as well as other planned annotations. Annotations are made available through a public web-based interface to enable data visualization of object attributes, promote data-driven geometric analysis, and provide a large-scale quantitative benchmark for research in computer graphics and vision. At the time of this technical report, ShapeNet has indexed more than 3,000,000 models, 220,000 models out of which are classified into 3,135 categories (WordNet synsets). In this report we describe the ShapeNet effort as a whole, provide details for all currently available datasets, and summarize future plans.

Building a LargeAnnotated Corpus of…Building a Large Annotated Corpus of English: The Penn TreebankThe Protein Data BankThe Protein Data BankThe Princeton ShapeBenchmarkThe Princeton Shape BenchmarkImageNet: A large-scalehierarchical image…ImageNet: A large-scale hierarchical image databaseLabelMe: Online ImageAnnotation and…LabelMe: Online Image Annotation and ApplicationsA probabilistic modelfor component-based…A probabilistic model for component-based shape synthesisExploring collections of3D models using fuzzy…Exploring collections of 3D models using fuzzy correspondencesSUN3D: A Database of BigSpaces Reconstructed…SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object LabelsLearning part-basedtemplates from large…Learning part-based templates from large collections of 3D shapesBeyond PASCAL: Abenchmark for 3D object…Beyond PASCAL: A benchmark for 3D object detection in the wildCreating consistentscene graphs using a…Creating consistent scene graphs using a probabilistic grammarSemantically-enriched 3Dmodels for common-sense…Semantically-enriched 3D models for common-sense knowledgeDeMoN: Depth and MotionNetwork for Learning…DeMoN: Depth and Motion Network for Learning Monocular Stereo3DMV: Joint3D-Multi-View Predictio…3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene SegmentationSpiderCNN: Deep Learningon Point Sets with…SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional FiltersPIFu: Pixel-AlignedImplicit Function for…PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationA Survey on DeepLearning Architectures…A Survey on Deep Learning Architectures for Image-based Depth ReconstructionCategory Level ObjectPose Estimation via…Category Level Object Pose Estimation via Neural Analysis-by-SynthesisSearching Efficient 3DArchitectures with…Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionKeypointNet: ALarge-Scale 3D Keypoint…KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human AnnotationsASFM-Net: AsymmetricalSiamese Feature Matchin…ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion3DStyleNet: Creating 3DShapes with Geometric…3DStyleNet: Creating 3D Shapes with Geometric and Texture Style VariationsPVNAS: 3D NeuralArchitecture Search Wit…PVNAS: 3D Neural Architecture Search With Point-Voxel ConvolutionGET3D: A GenerativeModel of High Quality 3…GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from ImagesShapeNet: AnInformation-Rich 3D…ShapeNet: An Information-Rich 3D Model RepositoryEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.