SHREC'16 track: Shape retrieval of low-cost RGB-D captures

Date

2016-05-08

Author

Pascoal, Pedro B.
Proença, Pedro
Gaspar, Filipe
Dias, Miguel Sales
Ferreira, Alfredo
Tatsuma, Atsushi
Aono, Masaki
Logoglu, K. Berker
Kalkan, Sinan
Temizel, Alptekin
Li, Bo
Johan, Henry
Lu, Yijuan
Seib, Viktor
Link, Norman
Paulus, Dietrich

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

36
views

0
downloads

RGB-D cameras allow to capture digital representations of objects in an easy and inexpensive way. Such technology enables ordinary users to capture everyday object into digital 3D representations. In this context, we present a track for the Shape Retrieval Contest, which focus on objects digitized using the latest version of Microsoft Kinect, namely, Kinect One. The proposed, track encompasses a dataset of two hundred objects and respective classification.

Subject Keywords

Information storage and retrieval, Information search and retrieval, Computational geometry and object modeling, Geometric algorithms, languages, and systems

URI

https://hdl.handle.net/11511/31624

DOI

https://doi.org/10.2312/3dor.20161090

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

SHREC 16 Partial Matching of Deformable Shapes Cosmo, Luca; Rodola, Emanuele; Bronstein, Michael; Torsello, Andrea; Cremers, Daniel; Sahillioğlu, Yusuf (null; 2016-06-15) Matching deformable 3D shapes under partiality transformations is a challenging problem that has received limited focus in the computer vision and graphics communities. With this benchmark, we explore and thoroughly investigate the robustness of existing matching methods in this challenging task. Participants are asked to provide a point-to-point correspondence (either sparse or dense) between deformable shapes undergoing different kinds of partiality transformations, resulting in a total of 400 matching pr...
Practical HDR A Simple and Effective Method for Merging High Dynamic Range Videos Akcora, Ezgi; Banterle, Francesco; Corsini, Massimiliano; Akyüz, Ahmet Oğuz; Scopigno, Roberto (2016-12-12) We introduce a novel algorithm for obtaining High Dynamic Range (HDR) videos from Standard Dynamic Range (SDR) videos with varying shutter speed or ISO per frame. This capturing technique represents today one of the most popular HDR video acquisition methods, thanks to the availability and the low cost of the equipment required; i.e., an off-the-shelf DSLR camera. However, naïvely merging SDR frames into an HDR video can produce artifacts such as ghosts (when the scene is dynamic), and blurry edges (when th...
Performance improvement of a 3d reconstruction algorithm using single camera images Kılıç, Varlık; Platin, Bülent Emre; Department of Mechanical Engineering (2005) In this study, it is aimed to improve a set of image processing techniques used in a previously developed method for reconstructing 3D parameters of a secondary passive target using single camera images. This 3D reconstruction method was developed and implemented on a setup consisting of a digital camera, a computer, and a positioning unit. Some automatic target recognition techniques were also included in the method. The passive secondary target used is a circle with two internal spots. In order to achieve...
Real-time FPGA firmware for VGA resolution infrared camera Çevik, Kami; Akın, Tayfun; Department of Electrical and Electronics Engineering (2019) Infrared cameras generally require pre-processing on raw image data in order to improve the output image quality. Raw output of the infrared cameras occupies a narrow part of the available dynamic range. Contrast enhancement is one of the pre-processing operations and used for improving dynamic range of the low contrast images. This thesis proposes an adaptive histogram equalization method for enhancing the contrast of long wavelength infrared camera output with 640×480 resolution and provides a FPGA implem...
Color Preserving HDR Fusion for Dynamic Scenes Karadağ, Gökdeniz; Akyüz, Ahmet Oğuz (2012-06-01) We present a novel algorithm to efficiently generate high quality high dynamic range (HDR) images. Our method is based on the idea of expanding the dynamic range of a reference image at granularity of tiles. In each tile, we use data from a single exposure, but different tiles can come from different exposures. We show that this approach is not only efficient and robust against camera and object movement, but also improves the color quality of the resulting HDR images. We compare our method against the comm...

Citation Formats

P. B. Pascoal et al., “SHREC′16 track: Shape retrieval of low-cost RGB-D captures,” 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/31624.