Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters
























22 Hits in 4.2 sec

PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation [article]

Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.2 MB)
https://web.archive.org/web/20200930082735/https://arxiv.org/pdf/1903.00709v4.pdf

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.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2019 pre-print arXiv:1903.00709v4 fatcat:2xuivqqaqrftvpfncnnzyewv5e

Other Versions

2019 pre-print
arXiv:1903.00709v3 fatcat:emo6fbck4nagdhpbke7yf6z6uu
2019 pre-print
arXiv:1903.00709v2 fatcat:icsts5q76bcmzo4etw2k643eiu
2019 pre-print
arXiv:1903.00709v1 fatcat:pysezhugynfyrgzoyxpy3mibpa
We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks.  ...  It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work.  ...  This work was supported in part by NSFC (61572507, 61532003, 61622212) and Natural Science Foundation of Hunan Province for Distinguished Young Scientists (2017JJ1002).  ... 
arXiv:1903.00709v5 fatcat:s3z2auyxnvcwlku2nsiruks5mm
Multiple Versions
Citation

Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu. "PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation." arXiv (2022)

PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation

Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.5 MB)
https://web.archive.org/web/20190610222449/http://openaccess.thecvf.com/content_CVPR_2019/papers/Yu_PartNet_A_Recursive_Part_Decomposition_Network_for_Fine-Grained_and_Hierarchical_CVPR_2019_paper.pdf

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.

We opt for topdown recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks.  ...  It achieves the stateof-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work.  ...  This work was supported in part by NSFC (61572507, 61532003, 61622212) and Natural Science Foundation of Hunan Province for Distinguished Young Scientists (2017JJ1002).  ... 
doi:10.1109/cvpr.2019.00972 dblp:conf/cvpr/YuLZZ019 fatcat:2q2qrv6ounblpgvopaqwkrwkrm
Citation

Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu. "PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation." 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019) 9491-9500

HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling [article]

Fenggen Yu, Yiming Qian, Francisca Gil-Ureta, Brian Jackson, Eric Bennett, Hao Zhang
2023 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.5 MB)
https://web.archive.org/web/20230126103635/https://arxiv.org/pdf/2301.10460v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL. The file type is application/pdf.

We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among  ...  Our labeling tool iteratively verifies or modifies part labels predicted by a deep neural network, with human feedback continually improving the network prediction.  ...  Datasets and Metrics Datasets. The Stanford PartNet [18] dataset is a common choice for fine-grained shape analysis [10, 25, 31] .  ... 
arXiv:2301.10460v1 fatcat:vfgmziphkngipbgavhor34ynje
Open Access
Citation

Fenggen Yu, Yiming Qian, Francisca Gil-Ureta, Brian Jackson, Eric Bennett, Hao Zhang. "HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling." arXiv (2023)

The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference [article]

R. Kenny Jones and Aalia Habib and Rana Hanocka and Daniel Ritchie
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (119.1 MB)
https://web.archive.org/web/20220614131554/https://arxiv.org/pdf/2106.12026v3.pdf

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.

Other Versions

2021 pre-print
arXiv:2106.12026v1 fatcat:eq45wgfsczhulc5a2j6n5i2l2m
2021 pre-print
arXiv:2106.12026v2 fatcat:al2kbi4ydfbcrc4zpfplv5xnty
We evaluate NGSP on the task of fine-grained semantic segmentation of manufactured 3D shapes from PartNet, where shapes have been decomposed into regions that correspond to part instance over-segmentations  ...  We propose the Neurally-Guided Shape Parser (NGSP), a method that learns how to assign fine-grained semantic labels to regions of a 3D shape.  ...  Renderings of part cuboids and point clouds were produced using the Blender Cycles renderer. This work was funded in parts by NSF award #1941808 and a Brown University Presidential Fellowship.  ... 
arXiv:2106.12026v3 fatcat:6hucvgphtrde5awdp54xyzb7n4
Multiple Versions
Citation

R. Kenny Jones and Aalia Habib and Rana Hanocka and Daniel Ritchie. "The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference." arXiv (2022)

DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation [article]

Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (40.2 MB)
https://web.archive.org/web/20220610083340/https://arxiv.org/pdf/2008.05440v4.pdf

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.

Other Versions

2020 pre-print
arXiv:2008.05440v1 fatcat:diw3vig52bd6xcnzdfrz62rawq
2020 pre-print
arXiv:2008.05440v2 fatcat:ru3pk3qovrbh5di4r6vxcrjqv4
2021 pre-print
arXiv:2008.05440v3 fatcat:gth6s7jmh5fbjogehj72o3exoe
To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry, and structure  ...  To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level.  ...  PartNet provides fine-grained, multiscale and hierarchical shape part segmentation for ShapeNet [Chang Fig. 8 . The gallery of shape reconstruction results on PartNet.  ... 
arXiv:2008.05440v4 fatcat:e42suegj2jf3zmkehp66tla6py
Multiple Versions
Citation

Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao. "DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation." arXiv (2022)

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation [article]

Chunyu Sun, Xin Tong, Yang Liu
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (16.8 MB)
https://web.archive.org/web/20220813064259/https://arxiv.org/pdf/2208.04766v1.pdf

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.

In this paper, we present a new method for 3D part instance segmentation.  ...  Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding.  ...  instance segmentation on PartNet 4.1.1 Experiments and comparison Dataset PartNet is a large-scale dataset with fine-grained and hierarchical part annotations.  ... 
arXiv:2208.04766v1 fatcat:vci5e6ylfzgedbizv5kzcex6nm
Open Access
Citation

Chunyu Sun, Xin Tong, Yang Liu. "Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation." arXiv (2022)

Learning Fine-Grained Segmentation of 3D Shapes without Part Labels [article]

Xiaogang Wang, Xun Sun, Xinyu Cao, Kai Xu, Bin Zhou
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.6 MB)
https://web.archive.org/web/20220115082222/https://arxiv.org/pdf/2103.13030v2.pdf

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.

Other Versions

2021 pre-print
arXiv:2103.13030v1 fatcat:vuszbtraszcuvhu3zzkqw5khru
This assumption, however, is impractical for learning fine-grained segmentation.  ...  We approach the problem with deep clustering, where the key idea is to learn part priors from a shape dataset with fine-grained segmentation but no part labels.  ...  This work was supported in part by National Key Research and Development Program of China (2018AAA0102200, 2019YFF0302902), and National Natural Science Foundation of China (61932003, 61532003).  ... 
arXiv:2103.13030v2 fatcat:vlwdfk53lbe7tgv7xhnogbny2e
Multiple Versions
Citation

Xiaogang Wang, Xun Sun, Xinyu Cao, Kai Xu, Bin Zhou. "Learning Fine-Grained Segmentation of 3D Shapes without Part Labels." arXiv (2022)

SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry [article]

Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang
2023 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (19.2 MB)
https://web.archive.org/web/20230307163755/https://arxiv.org/pdf/2302.10237v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL. The file type is application/pdf.

We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.  ...  Therefore for the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and their layout.  ...  ACKNOWLEDGMENT This work was supported by the Beijing Municipal Natural Science Foundation for Distinguished Young Scholars (No. JQ21013), the National Natural Science Foundation of China  ... 
arXiv:2302.10237v1 fatcat:ej4anosogbhdtfidififr2bpsa
Citation

Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang. "SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry." arXiv (2023)

DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation

Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao
2022 ACM Transactions on Graphics  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (5.5 MB)
https://web.archive.org/web/20220428011847/https://dl.acm.org/doi/pdf/10.1145/3526212

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.

To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured & geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry and structure,  ...  To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level.  ...  PartNet provides ine-grained, multi-scale and hierarchical shape part segmentation for ShapeNet [Chang et al. 2015 ] models.  ... 
doi:10.1145/3526212 fatcat:l54jkinxkbcl7jfbsmeabrnf5e
Citation

Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao. "DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation." ACM Transactions on Graphics (2022)

StructureNet: Hierarchical Graph Networks for 3D Shape Generation [article]

Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (19.0 MB)
https://web.archive.org/web/20200913154739/https://arxiv.org/pdf/1908.00575v1.pdf

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.

We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii  ...  We extensively evaluate the quality of the learned latent spaces for various shape families and show significant advantages over baseline and competing methods.  ...  We especially thank Kun Liu, Peilang Zhu, Yan Zhang, and Kai Xu for the help preparing binary symmetry hierarchies Wang et al. 2011a ] on PartNet [Mo et al. 2019] .  ... 
arXiv:1908.00575v1 fatcat:7wjjm7vqvvhfll6ncad6vvllny
Citation

Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas. "StructureNet: Hierarchical Graph Networks for 3D Shape Generation." arXiv (2019)

StructEdit: Learning Structural Shape Variations [article]

Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas
2019 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (8.3 MB)
https://web.archive.org/web/20200930135100/https://arxiv.org/pdf/1911.11098v1.pdf

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.

In a setting where the shapes themselves are encoded in terms of fine-grained part hierarchies, we demonstrate that a separate encoding of shape deltas or differences provides a principled way to deal  ...  Our approach is based on a conditional variational autoencoder for encoding and decoding shape deltas, conditioned on a source shape.  ...  The first dataset we use for training and evaluation is the PartNet dataset [26] generated from a subset of ShapeNet [7] with annotated hierarchical decomposition of each object into labelled parts  ... 
arXiv:1911.11098v1 fatcat:4dingljzlrbyrodjb3f37rcmei
Citation

Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas. "StructEdit: Learning Structural Shape Variations." arXiv (2019)

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding [article]

Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (15.0 MB)
https://web.archive.org/web/20210402190146/https://arxiv.org/pdf/2103.16397v2.pdf

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

2021 pre-print
arXiv:2103.16397v1 fatcat:g5vxk3xnj5a2dh3jlxx54p2azq
This involves categorizing, segmenting and reasoning of visual affordance.  ...  Based on this dataset, we provide three benchmarking tasks for evaluating visual affordance understanding, including full-shape, partial-view and rotation-invariant affordance estimations.  ...  Hierarchical segmentation was also addressed by a recursive part decomposition [31] .  ... 
arXiv:2103.16397v2 fatcat:5iqpr46jbndmjkw3b46hymbaku
Multiple Versions
Citation

Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia. "3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding." arXiv (2021)

VLGrammar: Grounded Grammar Induction of Vision and Language [article]

Yining Hong, Qing Li, Song-Chun Zhu, Siyuan Huang
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20210328163503/https://arxiv.org/pdf/2103.12975v1.pdf

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.

To provide a benchmark for the grounded grammar induction task, we collect a large-scale dataset, PartIt, which contains human-written sentences that describe part-level semantics for 3D objects.  ...  While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure.  ...  Acknowledgements The work reported herein was supported by ONR N00014-19-1-2153, ONR MURI N00014-16-1-2007, and DARPA XAI N66001-17-2-4029.  ... 
arXiv:2103.12975v1 fatcat:mx6q5dm3hrbi7lrtsm3ned7pja
Citation

Yining Hong, Qing Li, Song-Chun Zhu, Siyuan Huang. "VLGrammar: Grounded Grammar Induction of Vision and Language." arXiv (2021)

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

Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (2.7 MB)
https://web.archive.org/web/20200417221841/https://arxiv.org/pdf/2002.07995v2.pdf

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.

Other Versions

2020 pre-print
arXiv:2002.07995v1 fatcat:zqanuusvbvbxnlhu6lnzuxbb4a
In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been proposed for different applications.  ...  Therefore, in this survey, we review recent development in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations in  ...  PartNet provides a more detailed CAD model dataset with fine-grained, hierarchical part annotations, which brings more challenges and resources for 3D object applications such as semantic segmentation,  ... 
arXiv:2002.07995v2 fatcat:pustwlu5freypnccfrculkqvei
Open Access Multiple Versions
Citation

Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao. "A Survey on Deep Geometry Learning: From a Representation Perspective." arXiv (2020)

A survey on deep geometry learning: From a representation perspective

Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao
2020 Computational Visual Media  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.5 MB)
https://web.archive.org/web/20201108045900/https://link.springer.com/content/pdf/10.1007/s41095-020-0174-8.pdf

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.

In recent years, 3D computer vision and geometry deep learning have gained ever more attention. Many advanced techniques for 3D shapes have been proposed for different applications.  ...  Therefore, in this survey, we review recent developments in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations for  ...  PartNet [114] provides a more detailed CAD model dataset with fine-grained, hierarchical part annotations, bringing more challenges, and resources for 3D object applications such as semantic segmentation  ... 
doi:10.1007/s41095-020-0174-8 fatcat:kpoynaixq5esbek63bovybisfa
DOAJ
Citation

Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao. "A survey on deep geometry learning: From a representation perspective." Computational Visual Media 6.2 (2020) 113-133

« Previous Showing results 1 — 15 out of 22 results