A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering
[article]
2018
arXiv
pre-print
Preserved Fulltext
We call this approach neural (re-)rendering, and our live system "LookinGood". ...
We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution ...
LOOKINGOOD WITH NEURAL RE-RENDERING Existing real-time single and multiview performance capture pipelines [Dou et al. 2017 [Dou et al. , 2016 Newcombe et al. 2015; , estimate the geometry and texture ...
arXiv:1811.05029v1
fatcat:lxmoanmk75ez7dyg6xwnvcm7wm
LookinGood^π: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We propose LookinGood^π, a novel neural re-rendering approach that is aimed to (1) improve the rendering quality of the low-quality reconstructed results from human performance capture system in real-time ...
Our key idea is to utilize the rendered image of reconstructed geometry as the guidance to assist the prediction of person-specific details from few reference images, thus enhancing the re-rendered result ...
We summarize our contributions as follows: • We present LookinGood π , a real-time personindependent neural re-rendering approach, to enhance human performance capture, especially with sparse multi-view ...
arXiv:2112.08037v1
fatcat:pttx4etzfrfizmjowx3doyy2ji
Few-shot Neural Human Performance Rendering from Sparse RGBD Videos
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames, leading to deployment ...
We introduce a two-branch neural blending to combine the neural point render and classical graphics texturing pipeline, which integrates reliable observations over sparse key-frames. ...
In our neural renderer training, we set k to be 20 for a typical motion sequence with about 500 frames, leading to 4% sparsity of capture view sampling. ...
arXiv:2107.06505v1
fatcat:ilzslk4kvvgrri7svtvjhqwfze
Human View Synthesis using a Single Sparse RGB-D Input
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2112.13889v1 fatcat:kg3j6ohhcbgmribnisivg3v2oy
Additionally, an enhancer network leverages the overall fidelity, even in occluded areas from the original view, producing crisp renders with fine details. ...
Aiming to address these limitations, we present a novel view synthesis framework to generate realistic renders from unseen views of any human captured from a single-view sensor with sparse RGB-D, similar ...
Unsupervised Lookingood: Enhancing performance capture with real-time
learning of shape and pose with differentiable point clouds. neural re-rendering. ACM Trans. ...
arXiv:2112.13889v2
fatcat:u6e2uuinxra2lnrknjmrcsd6yq
Learning Dynamic View Synthesis With Few RGBD Cameras
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2204.10477v1 fatcat:fwurz5ysejd7ro3hbgf76iciwm
We generate feature point clouds from RGBD frames and then render them into free-viewpoint videos via a neural renderer. ...
The dataset consists of 43 multi-view RGBD video sequences of everyday activities, capturing complex interactions between human subjects and their surroundings. ...
We perform neural rendering with point clouds instead of feature-map-warping. ...
arXiv:2204.10477v2
fatcat:tfortvxrwrcthkcrnbxjdslf7y
State of the Art on Neural Rendering
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. ...
Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering ...
Figure 8 : 8 The LookinGood system [MBPY * 18] uses real-time neural re-rendering to enhance performance capture systems. Images taken from Martin-Brualla et al. [MBPY * 18]. ...
arXiv:2004.03805v1
fatcat:6qs7ddftkfbotdlfd4ks7llovq
Neural Re-Rendering of Humans from a Single Image
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The body model with the rendered feature maps is fed through a neural image-translation network that creates the final rendered colour image. ...
To address these challenges, we propose a new method for neural re-rendering of a human under a novel user-defined pose and viewpoint, given one input image. ...
Neural Re-Rendering of Humans from a Single Image ...
arXiv:2101.04104v1
fatcat:6snujhlbpbgd7nc4gcw62soivy
Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2012.15838v1 fatcat:qawzlkgbsffjljuesptr2yjx3q
To evaluate our approach, we create a multi-view dataset named ZJU-MoCap that captures performers with complex motions. ...
This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. ...
Lookingood: Enhancing performance capture with [53] Vincent Sitzmann, Michael Zollhöfer, and Gordon Wet-
real-time neural re-rendering. In SIGGRAPH Asia, 2018. 2 zstein. ...
arXiv:2012.15838v2
fatcat:cehzk5zuwvespkjwhbgp3tnolu
Few-shot Neural Human Performance Rendering from Sparse RGBD Videos
2021
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames, leading to deployment ...
We introduce a two-branch neural blending to combine the neural point render and classical graphics texturing pipeline, which integrates reliable observations over sparse key-frames. ...
In our neural renderer training, we set k to be 20 for a typical motion sequence with about 500 frames, leading to 4% sparsity of capture view sampling. ...
doi:10.24963/ijcai.2021/130
fatcat:cxxo23s4knc6ln3tkngnc2ys5u