- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Closed-Form Solution of Simultaneous Denoising and Hole Filling of Depth Image
摘要： This paper presents a novel Time-of-Flight (ToF) depth recovery algorithm minimizing a new quadratic energy function utilizing depth and infrared data. The proposed energy function consists of a filtering term and a reconstruction term to remove noise and fill holes simultaneously in a depth image. In the filtering term, a new multilateral weight is introduced by fully using available spatial, depth, and infrared information. In the reconstruction term, a Poisson equation for reconstructing a depth image from its gradients is used whereas the depth gradients inside hole regions are interpolated with the proposed infrared-guided moving least squares. The recovered depth data can be obtained by solving a sparse linear system derived from minimizing the proposed energy function. Experimental results demonstrate that the proposed algorithm provides good depth recovery performance without introducing texture copy or blur artifacts compared to the existing methods.
关键词： hole filling,inpainting,time-of-flight depth,denoising,quadratic energy function,Depth recovery
更新于2025-09-10 09:29:36
-
Implementation of Real-Time Post-Processing for High-Quality Stereo Vision
摘要： We propose a novel post-processing algorithm and architecture that simultaneously uses the passive and active stereo vision information to improve the reliability of the three-dimensional disparity in a hybrid stereo vision system. The proposed architecture consists of four steps — left-right consistency checking, semi-2D hole filling, a tiny adaptive variance checking, and a 2D weighted median filter. The experimental results show that the error rate of the proposed algorithm (5.77%) is less than that of a raw disparity (10.12%) for a real-world camera image having a 1,280 × 720 resolution and maximum disparity of 256. Moreover, for the famous Middlebury stereo image sets, the proposed algorithm’s error rate (8.30%) is also less than that of the raw disparity (13.7%). The proposed architecture is implemented on a single commercial field-programmable gate array using only 13.01% of slice resources, which achieves a rate of 60 fps for 1,280 × 720 stereo images with a disparity range of 256.
关键词： post processing,hole filling,variance check,FPGA,weighted median filter,Stereo vision,3D depth
更新于2025-09-10 09:29:36
-
2D-to-3D conversion using optical flow based depth generation and cross-scale hole filling algorithm
摘要： 3D display has become the inevitable trend of display technology. Converting the traditional and classical 2D videos to 3D videos is an important and effective measure to solve the shortage of 3D contents. The major work about 2D-to-3D video conversion is how to extract depth information from the 2D video, and synthesize a new image from the existing viewpoint. We propose a depth extraction method based on dense edge-preserving optical flow from 2D videos, reducing the matching error in textureless regions. Moreover, we use the Gaussian Pyramid and Laplace Pyramid at cross scales to fill the holes in the image at new view point after 3D warping. The experiments show that our results outperform state-of-the-art methods in visual effect and statistics.
关键词： Depth extraction,Cross-scale hole-filling,Dense optical flow,2D-to-3D
更新于2025-09-04 15:30:14