Depth filtering using total variation based video decomposition

Abstract

In vision based applications, depth plays a crucial role from different aspects. From 3D rendering to automation, precision in depth measurement is important for acceptable performances. Though several techniques have been proposed to capture depth map of a scene, the estimation is either erroneous or much expensive for regular usage. Thus, the demand for high accuracy depth measurement is prominent in the field of robotics and computer vision.In this paper, we propose a method to estimate high accuracy depth map from a raw depth map for both static and dynamic scenes. This depth filtering is done by exploiting the spatio.temporal information present in a depth video and by taking the color information of the scene into account.

Local activity-driven structural-preserving filtering for noise removal and image smoothing

“…To preserve edges and fine details while effectively removing noise, both local gradient and variance are incorporated into the diffusion model [26,27]. In [2,3,[28][29][30], anisotropic diffusion is applied to 3D image processing fields. In [31], anisotropic diffusion is utilized as a preprocessing of DIBR to improve its quality.…”

A novel switching bilateral filtering algorithm for depth map

“…Traditional 3D depth denoising methods are focused on fusing multiple consecutive noisy depths to get a higher quality: a method based on the correlation between aligned color and depth frames provided by such sensors [12,13]; spatial-temporal denoising approaches [14,15]; a deep-learning based approach which makes use of aligned gray images to denoise depth data [16]. Enhancing the quality of the depth map obtained with a single depth frame is an increasingly popular research task: wavelet denoising [17]; total variation regularization [18]; median filtering based on adaptive weighted Gaussian [19]; bilateral filter [20]; non-Local-Mean method [21].…”

“…In the last years, the following algorithms were proposed: an effective divide-and-conquer method for handling disocclusion of the synthesized image [22]; a depth filtering scheme based on exploiting the temporal information and color information [18]; a nonlinear down/upsampling filtering and a depth reconstruction multilateral filtering using a spatial resolution, boundary similarity, and coding artifacts features [23]; a 3D collaborative filtering in graph Fourier transform domain [24]; a weighted mode filter and joint bilateral filter where the joint bilateral kernel provides an optimal solution with the help of the joint histogram [25]; an adaptive method to denoise depth using Differential Histogram of Normal Vectors features along with a linear SVM [26]; a threephase depth map correction, including eliminating anomalies, segmentation, amendment and finally inter-frame and intra-frame filtering [27]; a method based on utilizing a combination of Gaussian kernel filtering and anisotropic filtering [28].…”