High Quality Novel View Synthesis Based on Low Resolution Depth Image and High Resolution Color Image

نویسندگان

  • Jui-Chiu Chiang
  • Zheng-Feng Liu
  • Wen-Nung Lie
چکیده

In this paper, a new technique to generate high resolution depth image is proposed. First, a low resolution depth map is obtained by the time-of-flight depth camera. Then a high resolution depth map for a given view is generated by depth warping followed by depth value refinement taking into account the color information at the given view. The edge in the final depth map is then processed by bilateral filtering for edge preserving. With the color image and the corresponding depth image, novel view synthesis can be carried out by depth image based rendering (DIBR). Experimental results show that the depth map generated by the proposed technique is able to ensure novel view images with high quality.

منابع مشابه

Depth Improvement for FTV Systems Based on the Gradual Omission of Outliers

Virtual view synthesis is an essential part of computer vision and 3D applications. A high-quality depth map is the main problem with virtual view synthesis. Because as compared to the color image the resolution of the corresponding depth image is low. In this paper, an efficient and confided method based on the gradual omission of outliers is proposed to compute reliable depth values. In the p...

متن کامل

Robust Fuzzy Content Based Regularization Technique in Super Resolution Imaging

Super-resolution (SR) aims to overcome the ill-posed conditions of image acquisition. SR facilitates scene recognition from low-resolution image(s). Generally assumes that high and low resolution images share similar intrinsic geometries. Various approaches have tried to aggregate the informative details of multiple low-resolution images into a high-resolution one. In this paper, we present a n...

متن کامل

A Deep Model for Super-resolution Enhancement from a Single Image

This study presents a method to reconstruct a high-resolution image using a deep convolution neural network. We propose a deep model, entitled Deep Block Super Resolution (DBSR), by fusing the output features of a deep convolutional network and a shallow convolutional network. In this way, our model benefits from high frequency and low frequency features extracted from deep and shallow networks...

متن کامل

Improved Content Aware Image Retargeting Using Strip Partitioning

Based on rapid upsurge in the demand and usage of electronic media devices such as tablets, smart phones, laptops, personal computers, etc. and its different display specifications including the size and shapes, image retargeting became one of the key components of communication technology and internet. The existing techniques in image resizing cannot save the most valuable information of image...

متن کامل

Image Retrieval Using Dynamic Weighting of Compressed High Level Features Framework with LER Matrix

In this article, a fabulous method for database retrieval is proposed.  The multi-resolution modified wavelet transform for each of image is computed and the standard deviation and average are utilized as the textural features. Then, the proposed modified bit-based color histogram and edge detectors were utilized to define the high level features. A feedback-based dynamic weighting of shap...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

متن کامل
عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012