Data-driven structural priors for shape completion

By Minhyuk Sung, Vladimir G. Kim, Roland Angst, Leonidas J. Guibas. 2015

194 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, 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 Graphics and Computer-Aided Design

In Geology

Citations in the corpus

Learning Shape Priors for Single-View 3D Completion and Reconstruction (2018, background): “…our ShapeHD aims to model ambiguity on the next level: even among the realistic shapes, there are still multiple shapes explaining the observation well (c). growing number of papers on exploiting shape structures and regularities [34,51], and papers on leveraging strong database priors [46,32,4].”
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, methodology): “Sung et al. [40] combine this idea with the detection of symmetries and operate on part-based model obtained from the database.”
EC-Net: an Edge-aware Point set Consolidation Network (2018, methodology): “Data-driven surface reconstruction techniques [2,3,4,5] are based on matching local portions (often denoted as patches) to a set of examples.”
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference (2017, methodology): “To address this issue, some recent works ( [24] [25]) involved the concept of part assembly.”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans (2017, methodology): “Other shape completion methods have been developed, including approaches that leverage symmetries in meshes or point clouds [40, 19, 26, 34, 37] or part-based structural priors derived from a database [38].”
Multi-content GAN for Few-Shot Font Style Transfer (2017, unknown): “Similarly, 3D models can be completed from a partial 3D shape [5, 28].”
PCN: Point Completion Network (2018, methodology): “Some [15, 24, 32, 34, 43] retrieve the complete shape directly while some [17, 19, 28, 45, 52] retrieve object parts and then assemble them to obtain the complete shape.”
Learning Representations and Generative Models for 3D Point Clouds (2017, methodology): “02 similarly to (Sung et al., 2015)) for class-specific networks that were trained with the EMD and CD losses respectively.”
Learning Shape Abstractions by Assembling Volumetric Primitives (2016, background): “In the domain of 3D shapes, the idea of exploiting compositionality has played a similarly important role for object representation, parsing, and manipulation.”
SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer (2021, background): “(1) Traditional point cloud completion methods [42, 1, 44, 26] usually assume a smooth surface of 3D shape, or utilize large-scaled complete shape dataset to infer the missing regions for incomplete shape.”
Morphing and Sampling Network for Dense Point Cloud Completion (2019, methodology): “Example-based approaches (Pauly et al. 2005; Sung et al. 2015; Shen et al. 2012) ﬁrst retrieve some similar models in a large shape database, and then deform and assemble the retrieved models to complete the partial shape.”
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, unknown): “10-dim [44] vs .”
SceneNN: A Scene Meshes Dataset with aNNotations (2016, methodology): “[30] used an object-part representation to achieve more robust completion.”
A Field Model for Repairing 3D Shapes (2016, background): “In [31], a match is confirmed by thresholding the distances between completed points and ground-truth points.”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, background): “It is possible to apply these deformation based approaches on a part level as opposed to the whole object level [47, 57].”