Caner Sahin

Dr. Caner Sahin

Gemsas, Istanbul, İstanbul, Turkey (Türkiye)
+1
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
THTomáš Hodaň
Tomáš Hodaň
FMFrank Michel
Frank Michel
EBEric Brachmann
Eric Brachmann
WKWadim Kehl
Wadim Kehl
ABAnders Glent Buch
Anders Glent Buch
CRCarsten Rother
Carsten Rother

1 October 2017
Verified
Conference Paper
Closed access
VBVassileios Balntas
Vassileios Balntas
ADAndreas Doumanoglou
Andreas Doumanoglou
Caner SahinCaner Sahin
Caner Sahin
JSJuil Sock
Juil Sock
RKRigas Kouskouridas
Rigas Kouskouridas
TKTae-Kyun Kim
Tae-Kyun Kim
In this paper we examine the effects of using object poses as guidance to learning robust features for 3D object pose estimation. Previous works have focused on learning feature embeddings based on metric learning with triplet comparisons and rely only on the qualitative distinction of similar and dissimilar pose labels. In contrast, we consider the exact pose differences between the training samples, and aim to learn embeddings such that the distances in the pose label space are proportional to the distances in the feature space. However, since it is less desirable to force the pose-feature correlation when objects are symmetric, we discuss the use of weights that reflect object symmetry when measuring the pose distances. Furthermore, end-to-end pose regression is investigated and is shown to further boost the discriminative power of feature learning, improving pose recognition accuracies. Experimental results show that the features that are learnt guided by poses, are significantly more discriminative than the ones learned in the traditional way, outperforming state-of-the-art works. Finally, we measure the generalisation capacity of pose guided feature learning in previously unseen scenes containing objects under different occlusion levels, and we show that it adapts well to novel tasks.

23 January 2019
Verified
Book Chapter
Closed access
PDF file
Caner SahinCaner Sahin
Caner Sahin
TKTae-Kyun Kim
Tae-Kyun Kim

27 October 2019
Verified
Book Chapter
Closed access
PDF file
Caner SahinCaner Sahin
Caner Sahin
GGGuillermo Garcia-Hernando
Guillermo Garcia-Hernando
JSJuil Sock
Juil Sock
TKTae-Kyun Kim
Tae-Kyun Kim

1 July 2017 in Image and Vision Computing
Verified
Journal Article
Closed access
Caner SahinCaner Sahin
Caner Sahin
RKRigas Kouskouridas
Rigas Kouskouridas
TKTae-Kyun Kim
Tae-Kyun Kim

1 December 2016
Verified
Conference Paper
Closed access
Caner SahinCaner Sahin
Caner Sahin
RKRigas Kouskouridas
Rigas Kouskouridas
TKTae-Kyun Kim
Tae-Kyun Kim
State-of-the-art techniques proposed for 6D object pose recovery depend on occlusion-free point clouds to accurately register objects in 3D space. To reduce this dependency, we introduce a novel architecture called Iterative Hough Forest with Histogram of Control Points that is capable of estimating occluded and cluttered objects' 6D pose given a candidate 2D bounding box. Our Iterative Hough Forest is learnt using patches extracted only from the positive samples. These patches are represented with Histogram of Control Points (HoCP), a “scale-variant” implicit volumetric description, which we derive from recently introduced Implicit B-Splines (IBS). The rich discriminative information provided by this scale-variance is leveraged during inference, where the initial pose estimation of the object is iteratively refined based on more discriminative control points by using our Iterative Hough Forest. We conduct experiments on several test objects of a publicly available dataset to test our architecture and to compare with the state-of-the-art.