2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
DOI: 10.1109/cvpr.2019.00459
|View full text |Cite
|
Sign up to set email alerts
|

Occupancy Networks: Learning 3D Reconstruction in Function Space

Abstract: With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learningbased 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

7
2,390
1
10

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 2,543 publications
(2,408 citation statements)
references
References 60 publications
7
2,390
1
10
Order By: Relevance
“…This approach shows its strength in reconstructing high-fidelity 3D geometry without having to keep a discretized representation of the entire output volume in memory simultaneously. Furthermore, unlike implicit surface representations using a global feature vector [29,32,10], PIFu utilizes fully convolutional image features, retaining local details present in an input image.…”
Section: Related Workmentioning
confidence: 99%
“…This approach shows its strength in reconstructing high-fidelity 3D geometry without having to keep a discretized representation of the entire output volume in memory simultaneously. Furthermore, unlike implicit surface representations using a global feature vector [29,32,10], PIFu utilizes fully convolutional image features, retaining local details present in an input image.…”
Section: Related Workmentioning
confidence: 99%
“…We show that this DSIF representation improves both reconstruction accuracy and generalization behavior over previous work -its F-Score results are better than the stateof-the-art [21] by 10.3 points for 3D autoencoding of test models from trained classes and by 17.8 points for unseen classes. We show that it dramatically reduces network parameter count -its local decoder requires approximately 0.4% of the parameters used by [21]. We show that it can be used to complete posed depth images -its depth completion results are 15.8 percentage points higher than [21].…”
Section: Resultsmentioning
confidence: 97%
“…sum of local 3D functions, each evaluated as the product of a Gaussian and a residual function predicted with a deep network. We describe a method for inferring a DSIF from a 3D surface or posed depth image by first predicting a structured decomposition into shape elements, encoding 3D points within each shape element using PointNet [27], and decoding them with a residual TinyOccNet [21]. This approach provides an end-to-end framework for encoding shapes in local regions arranged in a global structure.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…skirts or dresses. Implicit function based representations [71,56,46,48,31] might be beneficial to deal with different topologies, but they do not allow control. Although it is remarkable that our model can predict the occluded appearance of the person, the model struggles to predict high frequency detail and complex texture patterns.…”
Section: Discussionmentioning
confidence: 99%