Filters








26,009 Hits in 3.8 sec

Learning Shape Templates with Structured Implicit Functions [article]

Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William T. Freeman, Thomas Funkhouser
<span title="2019-04-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that structured implicit functions are suitable for learning and allow a network to smoothly and simultaneously fit multiple classes of shapes.  ...  In this paper, we investigate learning a general shape template from data.  ...  Conclusion This paper investigates using structured implicit functions to learn a template for a diverse collection of 3D shapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06447v1">arXiv:1904.06447v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lpr6pcbgf5hormxx6mjnimxmf4">fatcat:lpr6pcbgf5hormxx6mjnimxmf4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191023041415/https://arxiv.org/pdf/1904.06447v1.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/a9/37/a937a8061710c5dcc9111f4f150c528c1706b649.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06447v1" 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 Implicit Templates for 3D Shape Representation [article]

Zerong Zheng, Tao Yu, Qionghai Dai, Yebin Liu
<span title="2021-05-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our key idea is to formulate DIFs as conditional deformations of a template implicit function.  ...  Experiments show that our method can not only learn a common implicit template for a collection of shapes, but also establish dense correspondences across all the shapes simultaneously without any supervision  ...  To the best of our knowledge, our work is the first one to learn implicit function-based templates for a collection of shapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.14565v2">arXiv:2011.14565v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x4uhc2e2xjhwfgu2fzvyw73kre">fatcat:x4uhc2e2xjhwfgu2fzvyw73kre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201203230946/https://arxiv.org/pdf/2011.14565v1.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/8b/4b/8b4b32ae8d73752a07c6e4283a30f1cc39266104.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.14565v2" 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>

Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence [article]

Yu Deng, Jiaolong Yang, Xin Tong
<span title="2021-03-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With DIF, a 3D shape is represented by a template implicit field shared across the category, together with a 3D deformation field and a correction field dedicated for each shape instance.  ...  The learned DIF-Net can also provides reliable correspondence uncertainty measurement reflecting shape structure discrepancy.  ...  Implicit Shape Representation. Recent studies show that learning implicit functions for 3D shapes excels at representing complicated geometry [45, 43, 15, 25, 24, 4, 5, 50, 19, 29] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.13650v3">arXiv:2011.13650v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/io3mkkju2venzggbbth26fcftq">fatcat:io3mkkju2venzggbbth26fcftq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210331000858/https://arxiv.org/pdf/2011.13650v3.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/7d/0b/7d0bed447cdcd3923da31338d8e18ab0541b8fbe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.13650v3" 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>

Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images [article]

Jianfei Guo, Zhiyuan Yang, Xi Lin, Qingfu Zhang
<span title="2021-11-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present neural radiance fields (NeRF) with templates, dubbed Template-NeRF, for modeling appearance and geometry and generating dense shape correspondences simultaneously among objects of the same category  ...  Using periodic activation and feature-wise linear modulation (FiLM) conditioning, we introduce deep implicit templates on 3D data into the 3D-aware image synthesis pipeline NeRF.  ...  In this paper, we combine category-specific NeRF with deep implicit templates. We use a NeRF template to model common geometry, structure, and appearance of the objects within the same category.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.04237v1">arXiv:2111.04237v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sulvlx4y6vfntnyi5pur5nhvxq">fatcat:sulvlx4y6vfntnyi5pur5nhvxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211111194057/https://arxiv.org/pdf/2111.04237v1.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/35/ad/35add553d6afb3c30a152d2cd3175c7faba76778.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.04237v1" 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>

Implicit Mesh Reconstruction from Unannotated Image Collections [article]

Shubham Tulsiani, Nilesh Kulkarni, Abhinav Gupta
<span title="2020-07-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We represent the shape as an image-conditioned implicit function that transforms the surface of a sphere to that of the predicted mesh, while additionally predicting the corresponding texture.  ...  with learned pixel to surface mappings.  ...  Leveraging a single 3D template shape per category as initialization, we learn the category-level implicit shape space from image collections.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08504v1">arXiv:2007.08504v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rcqsmdwmmfdnricsb2wibmpjzu">fatcat:rcqsmdwmmfdnricsb2wibmpjzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200718010419/https://arxiv.org/pdf/2007.08504v1.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/30/44/3044b002ccfa7fdadf32cfcd4855d54df4ee5f2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08504v1" 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-GIF: Neural Generalized Implicit Functions for Animating People in Clothing [article]

Garvita Tiwari, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll
<span title="2021-08-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We draw inspiration from template-based methods, which factorize motion into articulation and non-rigid deformation, but generalize this concept for implicit shape learning to obtain a more flexible model  ...  We present Neural Generalized Implicit Functions(Neural-GIF), to animate people in clothing as a function of the body pose.  ...  neural implicit function learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.08807v2">arXiv:2108.08807v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hmrbgcg4ojhqroo366ynbew7mq">fatcat:hmrbgcg4ojhqroo366ynbew7mq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210826000733/https://arxiv.org/pdf/2108.08807v2.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/07/93/079356af9927335db05cba4348545381a30f3b6a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.08807v2" 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>

Local Deep Implicit Functions for 3D Shape [article]

Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, Thomas Funkhouser
<span title="2020-06-12">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Towards this end, we introduce Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions.  ...  input with consistency across diverse shape collections.  ...  For example, [13] recently proposed a network to encode shapes into Structured Implicit Functions (SIF), which represents an implicit function as a mixture of local Gaussian functions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.06126v2">arXiv:1912.06126v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/enbtwuhzkjbd7bfy2cdsywejwm">fatcat:enbtwuhzkjbd7bfy2cdsywejwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200616001249/https://arxiv.org/pdf/1912.06126v2.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/1912.06126v2" 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>

ShapeFlow: Learnable Deformations Among 3D Shapes [article]

Chiyu "Max" Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas Guibas
<span title="2021-06-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations.  ...  ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology, yet preserves fine geometric details.  ...  The learned deformation function Φ ij θ deforms the template shape Xj into Xi←j so that it is geometrically close to the target shape Xi.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.07982v2">arXiv:2006.07982v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aouuxvjhc5hb7furw36dpwqhya">fatcat:aouuxvjhc5hb7furw36dpwqhya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210628203032/https://arxiv.org/pdf/2006.07982v2.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/3f/b1/3fb122561ab9af1cc54a742a519480a20a667457.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.07982v2" 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>

Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images [article]

Heming Zhu, Lingteng Qiu, Yuda Qiu, Xiaoguang Han
<span title="2022-03-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Fueled by the power of deep learning techniques and implicit shape learning, recent advances in single-image human digitalization have reached unprecedented accuracy and could recover fine-grained surface  ...  To address this issue, we proposed a novel geometry inference framework ReEF that reconstructs topology-consistent layered garment mesh by registering the explicit garment template to the whole-body implicit  ...  The fine shape module is trained conditioned on a fixed coarse shape module with a learning rate of 1 × 10 −4 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.15007v1">arXiv:2203.15007v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mgtg7e46dbdkll4jq565qc7jx4">fatcat:mgtg7e46dbdkll4jq565qc7jx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220331014604/https://arxiv.org/pdf/2203.15007v1.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/ed/8b/ed8b8fe7528a47054d2c1cda4f366f9e6f57ee42.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.15007v1" 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>

A Multi-Implicit Neural Representation for Fonts [article]

Pradyumna Reddy, Zhifei Zhang, Matthew Fisher, Hailin Jin, Zhaowen Wang, Niloy J. Mitra
<span title="2022-01-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
of learned implict functions, without losing features (e.g., edges and corners).  ...  Instead, we propose how to train such a representation with only local supervision, while the proposed neural architecture directly finds globally consistent multi-implicits for font families.  ...  In addition, deep implicit functions model shapes spatially instead of modeling sequentially as aforementioned in deep learning based vector graphs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.06866v2">arXiv:2106.06866v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xvjww62tgfg57azgksnyx4ucve">fatcat:xvjww62tgfg57azgksnyx4ucve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112021147/https://arxiv.org/pdf/2106.06866v2.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/77/62/77627cbe633b7ac8bd89ffca87074d52501ea2cb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.06866v2" 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>

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion [article]

Julian Chibane, Thiemo Alldieck, Gerard Pons-Moll
<span title="2020-04-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, learned implicit functions have shown great promise as they produce continuous reconstructions.  ...  properties of recent learned implicit functions, but critically they can also retain detail when it is present in the input data, and can reconstruct articulated humans.  ...  We would like to thank Twindom for providing us with the scan data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.01456v2">arXiv:2003.01456v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6yoffv4s4vbbfppo3d3fquinnu">fatcat:6yoffv4s4vbbfppo3d3fquinnu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200418054138/https://arxiv.org/pdf/2003.01456v2.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/2003.01456v2" 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 explicit and implicit visual manifolds by information projection

Song-Chun Zhu, Kent Shi, Zhangzhang Si
<span title="">2010</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6r4znskbk5h2ngu345slqsm6eu" style="color: black;">Pattern Recognition Letters</a> </i> &nbsp;
In this paper, we start with small image patches and define two types of atomic subspaces: explicit manifolds of low dimensions for structural primitives and implicit manifolds of high dimensions for stochastic  ...  Finally, we integrate the implicit and explicit manifolds to form a primal sketch model as a generic representation in early vision and to generate a hybrid image template representation for object category  ...  Figure 22 : Competition of sketch (explicit) and texture (implicit) features in learning hybrid templates.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patrec.2009.07.020">doi:10.1016/j.patrec.2009.07.020</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wfxfyunlwzhfxpesib3v73ihx4">fatcat:wfxfyunlwzhfxpesib3v73ihx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808205128/http://www.stat.ucla.edu/%7Esczhu/papers/prl_manifold_learning.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/c3/2b/c32b117261fb249d30accb8a0cc50fc2c66cb1a1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patrec.2009.07.020"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose [article]

Thiemo Alldieck, Hongyi Xu, Cristian Sminchisescu
<span title="2021-08-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based  ...  In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh.  ...  limb differences, due to large structural differences compared to the GHUM template mesh.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10842v1">arXiv:2108.10842v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4aoggdkt5ba75fbzlg7ji7h7au">fatcat:4aoggdkt5ba75fbzlg7ji7h7au</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830112155/https://arxiv.org/pdf/2108.10842v1.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/05/f9/05f907e437a14d0db9b7479662d0cd587cd54634.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10842v1" 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>

A Survey on Deep Geometry Learning: From a Representation Perspective [article]

Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao
<span title="2020-04-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention.  ...  , mesh-based representation, implicit surface representation, etc.  ...  Implicit surface representation exploits implicit field functions, such as occupancy functions [67] and signed distance functions [116] , to describe the surface of 3D shapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.07995v2">arXiv:2002.07995v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pustwlu5freypnccfrculkqvei">fatcat:pustwlu5freypnccfrculkqvei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200417221841/https://arxiv.org/pdf/2002.07995v2.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/2002.07995v2" 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 Implicit Functions for Topology-Varying Dense 3D Shape Correspondence [article]

Feng Liu, Xiaoming Liu
<span title="2020-10-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Both functions are jointly learned with several effective loss functions to realize our assumption, together with the encoder generating the shape latent code.  ...  Conventional implicit functions estimate the occupancy of a 3D point given a shape latent code.  ...  Recently, some extensions have been proposed to learn deep structured [12, 13] or segmented implicit functions [9] , or separate implicit functions for shape parts [39] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12320v2">arXiv:2010.12320v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cwytcw3gjrhndb5ibqfvtnuhwi">fatcat:cwytcw3gjrhndb5ibqfvtnuhwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029151544/https://arxiv.org/pdf/2010.12320v2.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/97/74/97742b3a59a9300fe7175d56bb1e05f365de7e32.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12320v2" 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 26,009 results