Scale-invariant heat kernel signatures for non-rigid shape recognition

Bronstein, Michael M.; Kokkinos, Iasonas

doi:10.1109/cvpr.2010.5539838

Cited by 485 publications

(333 citation statements)

References 33 publications

Supporting

Mentioning

330

Contrasting

Unclassified

Order By: Relevance

“…One of them is to design powerful 3D shape signatures that can capture the intrinsic geometric information of the CAD models, with the motivation that the query and the database samples are essentially the same type of 3D models. To this end, various local features have been developed to describe the local geometry of 3D models, including MeshHoG as a 3D extension of the SIFT feature [7], Heat Kernel Signature [8] [11], and Intrinsic Shape Context [9]. Realizing the sensitivity to model noise for those local descriptors [15], researchers also proposed to use high-level topological features [19][20], or aggregate low-level features to mid-level representations such as the extended Bag-of-Words model [10][21] and graph correspondences [22].…”

Section: Related Workmentioning

confidence: 99%

“…More specifically, existing 3D shape retrieval approaches generally follow two popular frameworks, local feature matching with optional spatial verification [5][6] [7][8] [9] and the Bag-of-Feature scheme [10] [11], both of which require effective 3D local features. Although great progress has been made in 3D feature design, such as spin-image based descriptor [6], MeshDOG/MeshHOG [7], Heat Kernel Signature (HKS) [8] [11], and Intrinsic Shape Context (ISC) descriptor [9], these low-level shape features highly rely on the quality of the 3D models and ...…”

Section: Introductionmentioning

confidence: 99%

“…Although great progress has been made in 3D feature design, such as spin-image based descriptor [6], MeshDOG/MeshHOG [7], Heat Kernel Signature (HKS) [8] [11], and Intrinsic Shape Context (ISC) descriptor [9], these low-level shape features highly rely on the quality of the 3D models and ...…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, neither of these two frameworks explicitly address the challenge of partial models, resulting in degenerated performance in cross-domain 3D retrieval. For instance, previous study shows that the Scale-Invariant Heat Kernel Signature (SIHKS) achieves a high retrieval accuracy with CAD model queries [11], but significantly degrades for user-captured model queries [12]. To address these issues, spatial consistency checking has been used in both 2D [13] and 3D [10] cases.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. The recent advances of low-cost and mobile depth sensors dramatically extend the potential of 3D shape retrieval and analysis. While the traditional research of 3D retrieval mainly focused on searching by a rough 2D sketch or with a high-quality CAD model, we tackle a novel and challenging problem of cross-domain 3D shape retrieval, in which users can use 3D scans from low-cost depth sensors like Kinect as queries to search CAD models in the database. To cope with the imperfection of user-captured models such as model noise and occlusion, we propose a cross-domain shape retrieval framework, which minimizes the potential function of a Conditional Random Field to efficiently generate the retrieval scores. In particular, the potential function consists of two critical components: one unary potential term provides robust crossdomain partial matching and the other pairwise potential term embeds spatial structures to alleviate the instability from model noise. Both potential components are efficiently estimated using random forests with 3D local features, forming a Regression Tree Field framework. We conduct extensive experiments on two recently released user-captured 3D shape datasets and compare with several state-of-the-art approaches on the cross-domain shape retrieval task. The experimental results demonstrate that our proposed method outperforms the competing methods with a significant performance gain.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…Examples of such structures include multiscale heat kernel signatures [5][6][7], local photometric properties [8,9], eigenfunctions of the Laplace-Beltrami operator [10][11][12][13], triplets of points [14,15], and geodesic [2,3,16], diffusion [17], and commute time [10,18] distances. By defining a structure invariant under certain class of transformations (e.g.…”

Section: Introductionmentioning

confidence: 99%

Discrete Minimum Distortion Correspondence Problems for Non-rigid Shape Matching

Wang

Bronstein

et al. 2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Similarity and correspondence are two fundamental archetype problems in shape analysis, encountered in numerous application in computer vision and pattern recognition. Many methods for shape similarity and correspondence boil down to the minimum-distortion correspondence problem, in which two shapes are endowed with certain structure, and one attempts to find the matching with smallest structure distortion between them. Defining structures invariant to some class of shape transformations results in an invariant minimum-distortion correspondence or similarity. In this paper, we model shapes using local and global structures, formulate the invariant correspondence problem as binary graph labeling, and show how different choice of structure results in invariance under various classes of deformations.

show abstract

Fast accessing Web3D contents using lightweight progressive meshes

Wen

Xie

Jia

2015

Computer Animation & Virtual

View full text Add to dashboard Cite

Accessing Web3D contents is relatively slow through Internet under limited bandwidth. Preprocessing of 3D models can certainly alleviate the problem, such as 3D compression and progressive meshes (PM). But none of them considers the similarity between components of a 3D model, so that we could take advantage of this to further improve the efficiency. This paper proposes a similarity-aware data reduction method together with PM, called lightweight progressive meshes (LPM). LPM aims to excavate similar components in a 3D model, generates PM representation of each component left after removing redundant components, and organizes all the processed data using a structure called lightweight scene graph. The proposed LPM possesses four significant advantages. First, it can minimize the file size of 3D model dramatically without almost any precision loss. Because of this, minimal data is delivered. Second, PM enables the delivery to be progressive, so called streaming. Third, when rendering at client side, due to lightweight scene graph, decompression is not necessary and instanced rendering is fully exerted. Fourth, it is extremely efficient and effective under very limited bandwidth, especially when delivering large 3D scenes. Performance on real data justifies the effectiveness of our LPM, which improves the state-of-the-art in accessing Web3D contents.

show abstract

Scale-invariant heat kernel signatures for non-rigid shape recognition

Cited by 485 publications

References 33 publications

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Discrete Minimum Distortion Correspondence Problems for Non-rigid Shape Matching

Fast accessing Web3D contents using lightweight progressive meshes

Contact Info

Product

Resources

About