We present a novel depth image enhancement approach for RGB-D cameras such as the Kinect. Our approach employs optical flow of color images for refining the quality of corresponding depth images. We track every depth pixel over a sequence of frames in the temporal domain and use valid depth values of the same point for recovering missing and inaccurate information. We conduct experiments on different test datasets and present visually appealing results. Our method significantly reduces the temporal noise level and the flickering artifacts
Optical flow is widely used for describing motion cues in the scene, but limited by slow estimating ...
Depth is a useful information in vision to understand the geometrical properties of an environment....
One of the major research areas in computer vision is scene reconstruction from image streams. The a...
We present a novel depth image enhancement approach for RGB-D cameras such as the Kinect. Our approa...
In this paper, we propose a method of filtering depth maps that are automatically generated from vid...
This thesis proposes an approach utilizing guided techniques to refine depth images. Given a depth i...
In recent years, depth cameras (such as Microsoft Kinect and ToF cameras) have gained much popularit...
We propose a new method to enhance the depth images from RGB-D sensors, such as Kinects, by filling ...
Despite the tremendous progress in computer vision over the last decade, images captured by a digita...
When a video sequence is recorded in low-light conditions, the image often become noisy. Standard me...
Sophisticated video processing effects require both image and geometry information. We explore the p...
International audienceIn this paper we consider the problem of estimating a 3D motion field using mu...
This work presents a procedure for refining depth maps acquired using RGB-D (depth) cameras. With n...
In this paper, we present a novel depth map enhancement for real-time 3D reconstruction by the Micro...
Optical flow estimation is a difficult task given real-world video footage with camera and object bl...
Optical flow is widely used for describing motion cues in the scene, but limited by slow estimating ...
Depth is a useful information in vision to understand the geometrical properties of an environment....
One of the major research areas in computer vision is scene reconstruction from image streams. The a...
We present a novel depth image enhancement approach for RGB-D cameras such as the Kinect. Our approa...
In this paper, we propose a method of filtering depth maps that are automatically generated from vid...
This thesis proposes an approach utilizing guided techniques to refine depth images. Given a depth i...
In recent years, depth cameras (such as Microsoft Kinect and ToF cameras) have gained much popularit...
We propose a new method to enhance the depth images from RGB-D sensors, such as Kinects, by filling ...
Despite the tremendous progress in computer vision over the last decade, images captured by a digita...
When a video sequence is recorded in low-light conditions, the image often become noisy. Standard me...
Sophisticated video processing effects require both image and geometry information. We explore the p...
International audienceIn this paper we consider the problem of estimating a 3D motion field using mu...
This work presents a procedure for refining depth maps acquired using RGB-D (depth) cameras. With n...
In this paper, we present a novel depth map enhancement for real-time 3D reconstruction by the Micro...
Optical flow estimation is a difficult task given real-world video footage with camera and object bl...
Optical flow is widely used for describing motion cues in the scene, but limited by slow estimating ...
Depth is a useful information in vision to understand the geometrical properties of an environment....
One of the major research areas in computer vision is scene reconstruction from image streams. The a...
Add to ORKG