Partial Shape Queries for 3D Object Retrieval

Pratikakis, Ioannis; Savelonas, Michalis A.; Arnaoutoglou, Fotis; Ioannakis, George; Koutsoudis, Anestis; Theoharis, T.; Tran, Minh-Triet; Nguyen, Vinh-Tiep; Son, Pham Vu Hong; Nguyen, Hai-Dang; Le, Hoai-Bac; Tran, Ba-Huu; To, Quan H.; Truong, Minh-Hoang; Phan, Trong-Dat; Nguyen, Minh-Duc; Than, Thida; Mac, K.-N. C.; Minh, N.; Duong, A-D.; Furuya, Takahiko; Ohbuchi, Ryutarou; Aono, Masaki; Tashiro, Shoki; Pickup, David; Sun, Xianfang; Rosin, Paul L.; Martin, Ralph R.

doi:10.2312/3dor.20161091

Cited by 2 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed partial retrieval pipeline was evaluated on a set of real 3D object scans. The primary dataset chosen for this purpose is the SHREC'16 Partial Object Retrieval track dataset [39], which consists of a variety of historic artefacts, primarily ceramic pottery. We create additional partial query objects from this dataset to form a new augmented dataset of par- tial query objects, detailed in Section 6.1.…”

Section: Discussionmentioning

confidence: 99%

“…In the SHREC'16 Partial 3D Object Retrieval track [39], a number of additional view-based methods were introduced. Aono et al presented three variant methods which each encoded KAZE features [2] extracted from different object views with Vector of Locally Aggregated Descriptors (VLAD) [26], Gaussian of Local Distribution (GOLD) [47], and Fisher Vectors (FV) [37].…”

Section: Partial Object Retrievalmentioning

confidence: 99%

“…The motivation for using a voting threshold to exit jects as more query descriptors are processed, while using the proposed pipeline to locate the nearest neighbour of a single partial query object. Each line represents a single object from the SHREC'16 partial retrieval dataset [39]. For example, the best match (blue line) received 300 of the first 700 votes cast.…”

Section: Partial Retrieval Pipelinementioning

confidence: 99%

“…The SHREC'16 Partial Retrieval track dataset [39] has been chosen for the evaluation of the proposed retrieval pipeline. This allows direct comparison to results from other methods which were evaluated using this benchmark.…”

Section: Shrec'16 Dataset Augmentationmentioning

confidence: 99%

“…The proposed partial retrieval pipeline is compared against the results presented in the SHREC'16 Partial Shape Query track [39] as well as the results for the equivalent benchmark presented by Savelonas et al [45], which also includes results for the PANORAMA descriptor by Sfikas et al [48] and Global Fisher features [46]. As the source code of these works was not available, we have used the re- [39] and dFPFH, Global Fisher, and PANORAMA were taken from [45]. The latter does not show results for the 40% partiality queries which are therefore missing.…”

Section: Shrec'16 Partial Retrieval Performancementioning

confidence: 99%

See 4 more Smart Citations

Partial 3D Object Retrieval using Local Binary QUICCI Descriptors and Dissimilarity Tree Indexing

van Blokland,

Theoharis

2021

Preprint

Self Cite

View full text Add to dashboard Cite

A complete pipeline is presented for accurate and efficient partial 3D object retrieval based on Quick Intersection Count Change Image (QUICCI) binary local descriptors and a novel indexing tree. It is shown how a modification to the QUICCI query descriptor makes it ideal for partial retrieval. An indexing structure called Dissimilarity Tree is proposed which can significantly accelerate searching the large space of local descriptors; this is applicable to QUICCI and other binary descriptors. The index exploits the distribution of bits within descriptors for efficient retrieval. The retrieval pipeline is tested on the artificial part of SHREC'16 dataset with near-ideal retrieval results.

show abstract

Section: Discussionmentioning

confidence: 99%