Current IssuePrevious Issue   Next Issue

Volume 5 No. 3
05 September 2019

Dov Danon, Hadar Averbuch-Elor, Ohad Fried, Daniel Cohen-Or

2019, 5(3): 229-237.   doi:10.1007/s41095-019-0147-y
Abstract ( 9 HTML ( 0   PDF(896KB) ( 3 )   Save

A metric for natural image patches is an important tool for analyzing images. An efficient means of learning one is to train a deep network to map an image patch to a vector space, in which the Euclidean distance reflects patch similarity. Previous attempts learned such an embedding in a supervised manner, requiring the availability of many annotated images. In this paper, we present an unsupervised embedding of natural image patches, avoiding the need for annotated images. The key idea is th...

Kin-Ming Wong, Tien-Tsin Wong

2019, 5(3): 239-255.   doi:10.1007/s41095-019-0142-3
Abstract ( 18 HTML ( 0   PDF(4316KB) ( 18 )   Save

Learning-based techniques have recently been shown to be effective for denoising Monte Carlo rendering methods. However, there remains a quality gap to state-of-the-art handcrafted denoisers. In this paper, we propose a deep residual learning based method that outperforms both state-of-the-art handcrafted denoisers and learning-based denoisers. Unlike the indirect nature of existing learning-based methods (which e.g., estimate the parameters and kernel weights of an explicit feature ba...

Jesse Archer, Geoff Leach, Pyarelal Knowles

2019, 5(3): 257-265.   doi:10.1007/s41095-019-0144-1
Abstract ( 9 HTML ( 0   PDF(757KB) ( 4 )   Save

The concept of using multiple deep images, under a variety of different names, has been explored as a possible acceleration approach for finding ray-geometry intersections. We leverage recent advances in deep image processing from order independent transparency for fast building of a compound deep image (CDI ) using a coherent memory format well suited for raycasting. We explore the use of a CDI and raycasting for the problem of determining distance between virt...

Thuc Trinh Le, Andrés Almansa, Yann Gousseau, Simon Masnou

2019, 5(3): 267-291.   doi:10.1007/s41095-019-0145-0
Abstract ( 13 HTML ( 0   PDF(1759KB) ( 14 )   Save

We present a system for the removal of objects from videos. As input, the system only needs a user to draw a few strokes on the first frame, roughly delimiting the objects to be removed. To the best of our knowledge, this is the first system allowing the semi-automatic removal of objects from videos with complex backgrounds. The key steps of our system are the following: after initialization, segmentation masks are first refined and then automatically propagated through the video. Missing reg...

Minghai Chen, Fan Xu, Lin Lu

2019, 5(3): 293-302.   doi:10.1007/s41095-019-0143-2
Abstract ( 18 HTML ( 0   PDF(1088KB) ( 15 )   Save

Recent years have shown rapid development of digital fabrication techniques, making manufacturing individual models reachable for ordinary users. Thus, tools for designing customized objects in a user-friendly way are in high demand. In this paper, we tackle the problem of generating a collage of patterns along a given boundary, aimed at digital fabrication. We represent the packing space by a pipe-like closed shape along the boundary and use ellipses as packing elements for computing an init...

Andre Waschk, Jens Krüger

2019, 5(3): 303-310.   doi:10.1007/s41095-019-0146-z
Abstract ( 18 HTML ( 0   PDF(860KB) ( 14 )   Save

In this paper, we present a novel approach to automated route generation of global positioning system (GPS) artwork. The term GPS artwork describes the generation of drawings by leaving virtual traces on digital maps. Until now, the creation of these images has required a manual planning phase in which an artist designs the route by hand. Once the route for this artwork has been planned, GPS devices have been used to track the movement. Using our solution, the lengthy planning phase can be si...

Saritha Murali, V. K. Govindan, Saidalavi Kalady

2019, 5(3): 311-324.   doi:10.1007/s41095-019-0148-x
Abstract ( 11 HTML ( 0   PDF(2007KB) ( 15 )   Save

Shadow removal has evolved as a pre-processing step for various computer vision tasks. Several studies have been carried out over the past two decades to eliminate shadows from videos and images. Accurate shadow detection is an open problem because it is often considered difficult to interpret whether the darkness of a surface is contributed by a shadow incident on it or not. This paper introduces a color-model based technique to remove shadows from images. We formulate shadow removal as an o...