Results 251 to 260 of about 16,759,811 (301)

SketchyDepth: from Scene Sketches to RGB-D Images

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
Sketch-based content generation is a creative and fun activity suited to casual and professional users that has many different applications. Today it is possible to generate the geometry and appearance of a single object by sketching it. Yet, only the appearance can be synthesized from a sketch of a whole scene.
Berardi G., Salti S., Di Stefano L.
openaire   +1 more source

Kinematic Structures Estimation on the RGB-D Images

2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 2020
In this paper, we propose a system which detects and estimates the kinematic structures of objects in the indoor environment. We are interested in specific types of objects like doors, sliding doors, and drawers which are common in the human environment and very important taking into account the full autonomy of mobile robots. We assume that the mobile
Rafal Staszak, Milena Molska, Kamil Mlodzikowski, Justyna Ataman, Dominik Belter   +4 more
openaire   +1 more source

Incremental registration of RGB-D images

2012 IEEE International Conference on Robotics and Automation, 2012
An RGB-D camera is a sensor which outputs range and color information about objects. Recent technological advances in this area have introduced affordable RGB-D devices in the robotics community. In this paper, we present a real-time technique for 6-DoF camera pose estimation through the incremental registration of RGB-D images.
Ivan Dryanovski, Carlos Jaramillo, Jizhong Xiao   +2 more
openaire   +2 more sources

Supervoxels for human and clothes in RGB-D image

2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace & Electronic Systems (VITAE), 2014
In order to reconstruct human body and remodel clothes in virtual try on and size-fitting scenario, we preprocess the input point cloud into supervoxels through over-segmentation. Over-segmentation of an image into superpixels is a widely used preprocessing approach in image segmentation.
Feng Qi, Honggang Zhang 0002, Bo Zhang, Zhanyu Ma, Na Liu   +4 more
openaire   +1 more source

Reflection Removal Using RGB-D Images

2018 25th IEEE International Conference on Image Processing (ICIP), 2018
This paper proposes a novel reflection removal method for RGB-D images that achieve reflection removal and depth map recovery simultaneously. In general, there is a strong structure correlation between an RGB image and a depth map in gradient domain.
Toshihiro Shibata, Yuji Akai, Ryo Matsuoka   +2 more
openaire   +1 more source

Unsupervised Segmentation of RGB-D Images

2015
While unsupervised segmentation of RGB images has never led to results comparable to supervised segmentation methods, a surprising message of this paper is that unsupervised image segmentation of RGB-D images yields comparable results to supervised segmentation.
Zhuo Deng, Longin Jan Latecki
openaire   +2 more sources

Image retargeting using RGB-D camera

Multimedia Tools and Applications, 2014
Forimage retargeting, most approaches only use color information to tackle this problem. In this paper, we analyze both color and depth information captured by a RGB-D camera to maintain the structure and preserve important regions. Particularly, we present a content-aware image retargeting algorithm based on depth information.
Wei-Yang Lin, Chih-Fong Tsai, Pei-Chen Wu, Bo-Rong Chen   +3 more
openaire   +2 more sources

An Implementation of ResNet on the Classification of RGB-D Images

2020
Facial recognition is to identify human faces from an image. It is becoming more and more important these days as it can be applied in multiple industries, such as bank, airport, e-business, etc. Because of the broad application prospects, face recognition is actively developed and researched by many people, companies and academic organizations.
Tongyan Gong, Huiqian Niu
openaire   +2 more sources

Structured Images for RGB-D Action Recognition

2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017
This paper presents an effective yet simple video representation for RGB-D based action recognition. It proposes to represent a depth map sequence into three pairs of structured dynamic images at body, part and joint levels respectively through bidirectional rank pooling.
Pichao Wang, Shuang Wang 0001, Zhimin Gao, Yonghong Hou, Wanqing Li 0001   +4 more
openaire   +1 more source

Saliency Cuts on RGB-D Images

2018
Saliency cuts aims to segment salient objects from a given saliency map. The existing saliency cuts methods focus on dealing with RGB images and videos, but ignore the exploration of depth cue, which limit their performance on RGB-D images. In this paper, we propose a novel saliency cuts method on RGB-D images, which utilizes both color and depth cues ...
Yuantian Wang, Lei Huang 0004, Tongwei Ren, Yunfei Zhang   +3 more
openaire   +1 more source