2020 International Conference on 3D Vision (3DV) 2020
DOI: 10.1109/3dv50981.2020.00127
|View full text |Cite
|
Sign up to set email alerts
|

TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderer

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 12 publications
0
5
0
Order By: Relevance
“…Neural point cloud rendering has been studied in [KSL20; DZL∗20; AUL19]. These works mainly focus on rendering novel views from a single scene using a sparse set of input views.…”
Section: Related Workmentioning
confidence: 99%
“…Neural point cloud rendering has been studied in [KSL20; DZL∗20; AUL19]. These works mainly focus on rendering novel views from a single scene using a sparse set of input views.…”
Section: Related Workmentioning
confidence: 99%
“…NPBG [2] encodes the local geometric shapes and appearance by learning neural descriptors, which synthesizes high quality novel indoor views from point clouds. TRANSPR [13] extends NPBG by augmenting point descriptors with alpha values and replacing Z-buffer rasterization with ray marching, it is able to synthesize semi-transparent parts of the scene. ADOP [22] proposes a point-based differentiable neural rendering, where the parameters of all scenarios are optimized by designing the stages of the pipeline to be differentiable.…”
Section: Scene Synthesis By Neural Renderingmentioning
confidence: 99%
“…As with other point-based human models, the point cloud generated by POP can either be meshed using classical tools such as the Poisson Surface Reconstruction (PSR) [29], or directly rendered into realistic images using recent pointbased neural rendering techniques [2,30,50]. However, in this work, we do not rely on neural rendering to inpaint the gaps between the points.…”
Section: Training and Inferencementioning
confidence: 99%