Data‐Driven Shape Analysis and Processing

Xu, Kai; Kim, Vladimir G.; Huang, Qixing; Kalogerakis, Evangelos

doi:10.1111/cgf.12790

Cited by 35 publications

(19 citation statements)

References 210 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, they do not employ a generic class-specific model that would permit the continuous optimisation of a given object shape. As introduced in [42], low-dimensional shape representations can be obtained using one of a few approaches of manifold learning (e.g., PCA, kernel-PCA, Isomap, LLE, auto-encoder). However, unsupervised learning and the resulting optimisability of such representations are far from trivial, which is why the first lower-dimensional models employed in the literature are explicit.…”

Section: Review Of Current Slam Systems and Their Evolution Into Spatmentioning

confidence: 99%

Representations and Benchmarking of Modern Visual SLAM Systems

Cao

Kneip

2020

Sensors

View full text Add to dashboard Cite

Simultaneous Localisation And Mapping (SLAM) has long been recognised as a core problem to be solved within countless emerging mobile applications that require intelligent interaction or navigation in an environment. Classical solutions to the problem primarily aim at localisation and reconstruction of a geometric 3D model of the scene. More recently, the community increasingly investigates the development of Spatial Artificial Intelligence (Spatial AI), an evolutionary paradigm pursuing a simultaneous recovery of object-level composition and semantic annotations of the recovered 3D model. Several interesting approaches have already been presented, producing object-level maps with both geometric and semantic properties rather than just accurate and robust localisation performance. As such, they require much broader ground truth information for validation purposes. We discuss the structure of the representations and optimisation problems involved in Spatial AI, and propose new synthetic datasets that, for the first time, include accurate ground truth information about the scene composition as well as individual object shapes and poses. We furthermore propose evaluation metrics for all aspects of such joint geometric-semantic representations and apply them to a new semantic SLAM framework. It is our hope that the introduction of these datasets and proper evaluation metrics will be instrumental in the evaluation of current and future Spatial AI systems and as such contribute substantially to the overall research progress on this important topic.

show abstract

Section: Review Of Current Slam Systems and Their Evolution Into Spatmentioning

confidence: 99%

Representations and Benchmarking of Modern Visual SLAM Systems

Cao

Kneip

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…A large correspondence dataset [HKC*18] is used for training shape correspondence. These correspondence pairs are generated via a part‐based registration method and all the shapes are from ShapeNetCore dataset [XKH*16]. Each pair shapes have 10K correspondence points in the training dataset.…”

Section: Algorithmmentioning

confidence: 99%

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Jian-hui

Wang

Mao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

We present a novel deep learning approach to extract point‐wise descriptors directly on 3D shapes by introducing Siamese Point Networks, which contain a global shape constraint module and a feature transformation operator. Such geometric descriptor can be used in a variety of shape analysis problems such as 3D shape dense correspondence, key point matching and shape‐to‐scan matching. The descriptor is produced by a hierarchical encoder–decoder architecture that is trained to map geometrically and semantically similar points close to one another in descriptor space. Benefiting from the additional shape contrastive constraint and the hierarchical local operator, the learned descriptor is highly aware of both the global context and local context. In addition, a feature transformation operation is introduced in the end of our networks to transform the point features to a compact descriptor space. The feature transformation can make the descriptors extracted by our networks unaffected by geometric differences in shapes. Finally, an N‐tuple loss is used to train all the point descriptors on a complete 3D shape simultaneously to obtain point‐wise descriptors. The proposed Siamese Point Networks are robust to many types of perturbations such as the Gaussian noise and partial scan. In addition, we demonstrate that our approach improves state‐of‐the‐art results on the BHCP benchmark.

show abstract

“…The key point of data‐driven methods is to improve the analysis and processing of individual shapes by analyzing and aggregating information from a set of shapes. We refer the reader to the survey on data‐driven shape analysis and processing techniques [XKHK15]. The applications of such techniques include a variety of methods such as shape retrieval [TV08, LBBC14], shape reconstruction [PMG*05, GSH*07] and matching [VKZHCO11].…”

Section: Related Workmentioning

confidence: 99%

“…They devote themselves to automatically mining latent patterns in geometry and structure of shapes, instead of relying on hard‐coded rules or explicitly programmed instructions. With these learned patterns serving as strong priors, many geometry processing applications can be solved more accurately and efficiently [XKHK15].…”

Section: Introductionmentioning

confidence: 99%

Data‐Driven Sparse Priors of 3D Shapes

Remil

Xie

et al. 2017

Computer Graphics Forum

View full text Add to dashboard Cite

We present a sparse optimization framework for extracting sparse shape priors from a collection of 3D models. Shape priors are defined as point-set neighborhoods sampled from shape surfaces which convey important information encompassing normals and local shape characterization. A 3D shape model can be considered to be formed with a set of 3D local shape priors, while most of them are likely to have similar geometry. Our key observation is that the local priors extracted from a family of 3D shapes lie in a very low-dimensional manifold. Consequently, a compact and informative subset of priors can be learned to efficiently encode all shapes of the same family. A comprehensive library of local shape priors is first built with the given collection of 3D models of the same family. We then formulate a global, sparse optimization problem which enforces selecting representative priors while minimizing the reconstruction error. To solve the optimization problem, we design an efficient solver based on the Augmented Lagrangian Multipliers method (ALM). Extensive experiments exhibit the power of our data-driven sparse priors in elegantly solving several high-level shape analysis applications and geometry processing tasks, such as shape retrieval, style analysis and symmetry detection.

show abstract

Data‐Driven Shape Analysis and Processing

Cited by 35 publications

References 210 publications

Representations and Benchmarking of Modern Visual SLAM Systems

Representations and Benchmarking of Modern Visual SLAM Systems

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Data‐Driven Sparse Priors of 3D Shapes

Contact Info

Product

Resources

About