2019
DOI: 10.1109/tpami.2018.2868195
|View full text |Cite
|
Sign up to set email alerts
|

Dense 3D Object Reconstruction from a Single Depth View

Abstract: In this paper, we propose a novel approach, 3D-RecGAN++, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of $256^… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
124
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 130 publications
(124 citation statements)
references
References 60 publications
0
124
0
Order By: Relevance
“…Another way to improve the resolution of volumetric techniques is by using multi-staged approaches [25], [27], [34], [41], [42]. The first stage recovers a low resolution voxel grid, say 32 3 , using an encoder-decoder architecture.…”
Section: Coarse-to-fine Refinementmentioning
confidence: 99%
See 3 more Smart Citations
“…Another way to improve the resolution of volumetric techniques is by using multi-staged approaches [25], [27], [34], [41], [42]. The first stage recovers a low resolution voxel grid, say 32 3 , using an encoder-decoder architecture.…”
Section: Coarse-to-fine Refinementmentioning
confidence: 99%
“…The subsequent stages, which function as upsampling networks, refine the reconstruction by focusing on local regions. Yang et al [42] used an up-sampling module which simply consists of two up-convolutional layers. This simple up-sampling module upgrades the output 3D shape to a higher resolution of 256 3 .…”
Section: Coarse-to-fine Refinementmentioning
confidence: 99%
See 2 more Smart Citations
“…SSCNet [40] combined these two tasks together and showed that segmentation and completion can benefit from each other. In order to generate high resolution 3D structure, various methods had been explored, such as long short-term memorized [15], coarse-to-fine strategy [5], 3D generative adversarial network [47], and inverse discrete cosine transform [22]. Recently, segmentation and completion are both benefited from these advanced 3D deep learning methods described in section 2.1.…”
Section: D Semantic Segmentation and Shape Completionmentioning
confidence: 99%