Efficient Single-View 3D Co-segmentation Using Shape Similarity and Spatial Part Relations

Araslanov, Nikita; Koo, Seongyong; Gall, Jüergen; Behnke, Sven

doi:10.1007/978-3-319-45886-1_24

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Part Segmentation: Others have studied how to decompose mesh collections into consistent sets of semantic parts, either through geometric [14] or learned methods [1,12,21,27]. These methods differ from ours in that they depend on labeled examples to learn the shapes and arrangements of semantic parts within specific classes.…”

Section: Related Workmentioning

confidence: 99%

Learning Shape Templates With Structured Implicit Functions

Genova

Cole

Vlasic

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

347

272

View full text Add to dashboard Cite

Figure 1. This paper introduces Deep Structured Implicit Functions, a 3D shape representation that decomposes an input shape (mesh on left in every triplet) into a structured set of shape elements (colored ellipses on right) whose contributions to an implicit surface reconstruction (middle) are represented by latent vectors decoded by a deep network. AbstractThe goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations. Towards this end, we introduce Deep Structural Implicit Functions (DSIF), a 3D shape representation that decomposes space into a structured set of local deep implicit functions. We provide networks that infer the space decomposition and local deep implicit functions from a 3D mesh or posed depth image. During experiments, we find that it provides 10.3 points higher surface reconstruction accuracy (F-Score) than the state-of-the-art (OccNet), while requiring fewer than 1% of the network parameters. Experiments on posed depth image completion and generalization to unseen classes show 15.8 and 17.8 point improvements over the state-of-the-art, while producing a structured 3D representation for each input with consistency across diverse shape collections.

show abstract