Filters








35,943 Hits in 6.1 sec

Neural Re-Rendering of Humans from a Single Image [article]

Kripasindhu Sarkar, Dushyant Mehta, Weipeng Xu, Vladislav Golyanik, Christian Theobalt
<span title="2021-01-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Human re-rendering from a single image is a starkly under-constrained problem, and state-of-the-art algorithms often exhibit undesired artefacts, such as over-smoothing, unrealistic distortions of the  ...  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  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04104v1">arXiv:2101.04104v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6snujhlbpbgd7nc4gcw62soivy">fatcat:6snujhlbpbgd7nc4gcw62soivy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210117215704/https://arxiv.org/pdf/2101.04104v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/07/77/0777624a09ebe3f64152d551c1eda7ad2701b472.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04104v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Human View Synthesis using a Single Sparse RGB-D Input [article]

Phong Nguyen, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung
<span title="2021-12-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
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  ...  We show our method generates high-quality novel views of synthetic and real human actors given a single sparse RGB-D input.  ...  How- unseen views of any human captured from a single-view sen- ever, synthesizing novel views of humans in motion re-  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.13889v2">arXiv:2112.13889v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u6e2uuinxra2lnrknjmrcsd6yq">fatcat:u6e2uuinxra2lnrknjmrcsd6yq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220106022621/https://arxiv.org/pdf/2112.13889v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/85/a1/85a11b5c1b13c3b1d859abb0464afe1b9ea17f9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.13889v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

EgoRenderer: Rendering Human Avatars from Egocentric Camera Images [article]

Tao Hu, Kripasindhu Sarkar, Lingjie Liu, Matthias Zwicker, Christian Theobalt
<span title="2021-11-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset.  ...  Our system renders photorealistic novel views of the actor and her motion from arbitrary virtual camera locations.  ...  We refer to the human re-rendering method [37] as Fea-Net (short for FeatureNet), which is the state of the art in human re-enactment and novel view rendering when this project was developed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12685v1">arXiv:2111.12685v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ibpmcwfv2zclzmdvc7ivt26kfy">fatcat:ibpmcwfv2zclzmdvc7ivt26kfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211127142930/https://arxiv.org/pdf/2111.12685v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/62/16/6216c3d5981d83435c3bfa3c41f6994427356f19.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12685v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Point-Based Modeling of Human Clothing [article]

Ilya Zakharkin, Kirill Mazur, Artur Grigorev, Victor Lempitsky
<span title="2021-10-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Using the learned model, we can infer the geometry of new outfits from as little as a single image, and perform outfit retargeting to new bodies in new poses.  ...  and to re-render the captured outfits.  ...  It proposes a virtual wardrobe of pre-fitted garments, and is also able to fit new outfits from a single image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08230v3">arXiv:2104.08230v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/as6lq3tibng5feldiayurusacq">fatcat:as6lq3tibng5feldiayurusacq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211009025922/https://arxiv.org/pdf/2104.08230v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bc/71/bc716c0aa88a5015b0c80f4555a07b6a68afc965.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08230v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

LookinGood^π: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture [article]

Xiqi Yang, Kewei Yang, Kang Chen, Weidong Zhang, Weiwei Xu
<span title="2021-12-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
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  ...  Neural re-rendering time analysis We analyze the re-rendering time of our approach on a single NVIDIA V100, with the 1024 × 512 resolution of both the rendered input and output image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08037v1">arXiv:2112.08037v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pttx4etzfrfizmjowx3doyy2ji">fatcat:pttx4etzfrfizmjowx3doyy2ji</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211217141849/https://arxiv.org/pdf/2112.08037v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/04/a1/04a178c02ea7a0ee41550bcf750ab9690b799698.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08037v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

State of the Art on Neural Rendering [article]

Ayush Tewari, Ohad Fried, Justus Thies, Vincent Sitzmann, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nießner, Rohit Pandey, Sean Fanello (+7 others)
<span title="2020-04-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
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  ...  With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists.  ...  For example, work on (re-)rendering faces has primarily focused on processing a single person in a short video clip.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.03805v1">arXiv:2004.03805v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6qs7ddftkfbotdlfd4ks7llovq">fatcat:6qs7ddftkfbotdlfd4ks7llovq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200410225440/https://arxiv.org/pdf/2004.03805v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.03805v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deferred Neural Rendering: Image Synthesis using Neural Textures [article]

Justus Thies and Michael Zollhöfer and Matthias Nießner
<span title="2019-04-28">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
(re-)renderings.  ...  To address this challenging problem, we introduce Deferred Neural Rendering, a new paradigm for image synthesis that combines the traditional graphics pipeline with learnable components.  ...  Figure 8: In uence of the neural texture resolution on rerendering. Sample images of re-renderings using single neural textures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.12356v1">arXiv:1904.12356v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r3vfiidi4fdgpnbr6phlvhsuuu">fatcat:r3vfiidi4fdgpnbr6phlvhsuuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929123950/https://arxiv.org/pdf/1904.12356v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e8/20/e82075b75c987c21ab51027842610792dbfd73eb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.12356v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

BANMo: Building Animatable 3D Neural Models from Many Casual Videos [article]

Gengshan Yang, Minh Vo, Natalia Neverova, Deva Ramanan, Andrea Vedaldi, Hanbyul Joo
<span title="2021-12-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
On real and synthetic datasets, BANMo shows higher-fidelity 3D reconstructions than prior works for humans and animals, with the ability to render realistic images from novel viewpoints and poses.  ...  BANMo builds high-fidelity, articulated 3D models (including shape and animatable skinning weights) from many monocular casual videos in a differentiable rendering framework.  ...  Online and body from a single image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.12761v2">arXiv:2112.12761v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/creiz2vswzdozoghhury7g5aza">fatcat:creiz2vswzdozoghhury7g5aza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220104012556/https://arxiv.org/pdf/2112.12761v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/09/5909ff87cf05db435930a55e1a9cf5e0a435115e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.12761v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering [article]

Liao Wang, Ziyu Wang, Pei Lin, Yuheng Jiang, Xin Suo, Minye Wu, Lan Xu, Jingyi Yu
<span title="2021-08-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To fill this gap, in this paper we propose a neural interactive bullet-time generator (iButter) for photo-realistic human free-viewpoint rendering from dense RGB streams, which enables flexible and interactive  ...  Recent neural advances still lack the controllable and interactive bullet-time design ability for human free-viewpoint rendering, especially under the real-time, dynamic and general setting for our trajectory-aware  ...  Recently, some work [20, 21, 32] has been used to apply deep learning methods to recover the geometry and texture of the human body from a single image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05577v1">arXiv:2108.05577v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvsqh2uwojcrfkrjvl6zdgy2w4">fatcat:kvsqh2uwojcrfkrjvl6zdgy2w4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210816054921/https://arxiv.org/pdf/2108.05577v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/68/bb68012134ada92309e4e0cceba97c388851ff76.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05577v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans [article]

Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou
<span title="2021-03-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views.  ...  To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable  ...  recover 3D human geometry and texture from a single (Section 3.1).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.15838v2">arXiv:2012.15838v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cehzk5zuwvespkjwhbgp3tnolu">fatcat:cehzk5zuwvespkjwhbgp3tnolu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210416130231/https://arxiv.org/pdf/2012.15838v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/af/8f/af8faec7c0b8f4b2a28d42a86e0e7d499016c560.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.15838v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions [article]

Yuheng Jiang, Suyi Jiang, Guoxing Sun, Zhuo Su, Kaiwen Guo, Minye Wu, Jingyi Yu, Lan Xu
<span title="2022-03-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, we introduce a layer-wise human-object texture rendering scheme, which combines volumetric and image-based rendering in both spatial and temporal domains to obtain photo-realistic results.  ...  In this paper, we propose NeuralHOFusion, a neural approach for volumetric human-object capture and rendering using sparse consumer RGBD sensors.  ...  ., 6}). ( 5 ) Same as neural human blending, Îj is the warped image of nearby source view I j from G oa . O j denotes the occlusion map. Novel view images will be generated like Eqn. 4.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.12825v3">arXiv:2202.12825v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5jj4wixl4rg4fdycf5sbdp4wha">fatcat:5jj4wixl4rg4fdycf5sbdp4wha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220303053208/https://arxiv.org/pdf/2202.12825v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/53/955320b68f7cf8db08b11bfe61755730a3ea4571.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.12825v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Neural Models for Illumination Estimation and Relighting: A Survey

Farshad Einabadi, Jean‐Yves Guillemaut, Adrian Hilton
<span title="2021-06-09">2021</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p2lpq6bugfcqxk44anrm6yki4m" style="color: black;">Computer graphics forum (Print)</a> </i> &nbsp;
Recently, the application of deep neural computing to illumination estimation, relighting and inverse rendering has shown promising results.  ...  reality or to render new images under novel lighting or viewpoints.  ...  Figure 5 shows the extracted scene elements from a single input image and then used for re-rendering the shading. Yu et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.14283">doi:10.1111/cgf.14283</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iaidifr5m5gwvmg3exbzvyrrem">fatcat:iaidifr5m5gwvmg3exbzvyrrem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718091708/https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/cgf.14283" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3c/28/3c288f401b05b421cb71b26a16ec2ab215442d3e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.14283"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction [article]

ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer, Dimitris Samaras
<span title="2020-12-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The facial details are represented as a vertex displacement map and used then by a Neural Renderer to photo-realistically render novel images of any single image in any desired expression and view.  ...  In this work, we introduce FaceDet3D, a first-of-its-kind method that generates - from a single image - geometric facial details that are consistent with any desired target expression.  ...  Acknowledgements This work is supported in part by a Google Daydream Research award, by the Spanish government with projects HuMoUR TIN2017-90086-R and María de Maeztu Seal of Excellence MDM-2016-0656,  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07999v3">arXiv:2012.07999v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/byexpip5ijhubhdcdn3jlziq4y">fatcat:byexpip5ijhubhdcdn3jlziq4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201228102413/https://arxiv.org/pdf/2012.07999v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7e/28/7e28c32327c85fabff3923c934dda9cf146b7c85.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07999v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting [article]

Zian Wang, Jonah Philion, Sanja Fidler, Jan Kautz
<span title="2021-10-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image.  ...  properties with the re-rendering constraint.  ...  To jointly predict intrinsic prop-erties and 3D VSG lighting from a single image, we split our pipeline into four submodules, with three neural network modules and one differentiable rendering module.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06061v2">arXiv:2109.06061v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wph767olhretdb2fny5xe5xjxq">fatcat:wph767olhretdb2fny5xe5xjxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211023012359/https://arxiv.org/pdf/2109.06061v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fd/04/fd04993554984a6c0d9ef8c8348f9bc11a1817a6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06061v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions [article]

Guoxing Sun, Xin Chen, Yizhang Chen, Anqi Pang, Pei Lin, Yuheng Jiang, Lan Xu, Jingya Wang, Jingyi Yu
<span title="2021-08-03">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a neural human performance capture and rendering system to generate both high-quality geometry and photo-realistic texture of both human and objects under challenging interaction  ...  To deal with complex occlusions raised by human-object interactions, we adopt a layer-wise scene decoupling strategy and perform volumetric reconstruction and neural rendering of the human and object.  ...  Different from [75] with only a single RGB input, we use pixel-aligned image features from the multi-view inputs and concatenate them with our encoded voxel-aligned features.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00362v2">arXiv:2108.00362v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qyiprwqeoff3ldblcvujeddqiu">fatcat:qyiprwqeoff3ldblcvujeddqiu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210805140116/https://arxiv.org/pdf/2108.00362v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/b1/9cb12a28abe74ab17826c47cd980efdfad94c01d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00362v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 35,943 results