As a promising alternative to VR head-mounted displays, current autostereoscopic displays and light field displays require high GPU consumption for multiple-view rendering and do not display different scenes for multiple viewers with motion parallax. Building upon prior work demonstrating how GPU utilization can be reduced by only rendering visible views, we propose an innovative approach to only render the visible views of different scenes towards multiple viewers' eyes. Moreover, we found that the number of visible views decreases as the viewing distances increase. Thus, a dynamic approach can be taken to adjust the number of rendered views according to viewers distance from the display. This approach can be easily adapted to the off-the-shelf light field displays to display different 3D scenes for at least two viewers according to their head positions with reduced GPU costs.

SAR image registration is a crucial problem in SAR image processing since the registration results with high precision are conducive to improving the quality of other problems, such as change detection of SAR images. Recently, for most DL-based SAR image registration methods, the problem of SAR image registration has been regarded as a binary classification problem with matching and non-matching categories to construct the training model, where a fixed scale is generally set to capture pair image blocks corresponding to key points to generate the training set, whereas it is known that image blocks with different scales contain different information, which affects the performance of registration. Moreover, the number of key points is not enough to generate a mass of class-balance training samples. Hence, we proposed a new method of SAR image registration that meanwhile utilizes the information of multiple scales to construct the matching models. Specifically, considering that the number of training samples is small, deep forest was employed to train multiple matching models. Moreover, a multi-scale fusion strategy is proposed to integrate the multiple predictions and obtain the best pair matching points between the reference image and the sensed image. Finally, experimental results on four datasets illustrate that the proposed method is better than the compared state-of-the-art methods, and the analyses for different scales also indicate that the fusion of multiple scales is more effective and more robust for SAR image registration than one single fixed scale.

In SAR image registration, most existing methods consider the image registration as a two-classification problem to construct the pair training samples for training the deep model. However, it is difficult to obtain a mass of given matched-points directly from SAR images as the training samples. Based on this, we propose a multi-class double-transformation network for SAR image registration based on Swin-Transformer. Different from existing methods, the proposed method directly considers each key point as an independent category to construct the multi-classification model for SAR image registration. Then, based on the key points from the reference and sensed images, respectively, a double-transformation network with two branches is designed to search for matched-point pairs. In particular, to weaken the inherent diversity between two SAR images, key points from one image are transformed to the other image, and the transformed image is used as the basic image to capture sub-images corresponding to all key points as the training and testing samples. Moreover, a precise-matching module is designed to increase the reliability of the obtained matched-points by eliminating the inconsistent matched-point pairs given by two branches. Finally, a series of experiments illustrate that the proposed method can achieve higher registration performance compared to existing methods.

No abstract

This short paper presents a method called Variable Rate Ray Tracing to reduce the performance cost with minimal quality loss when facilitating hardware-accelerated ray tracing for Virtual Reality. This method is applied to the ray generation stage in the ray tracing pipeline to vary the ray tracing rate based on the scene specific information. The method uses 3 different control policies to effectively reduce rays generated per second for various needs. Based on the benchmark, this method can improve more than 30% frames per second(FPS) on current mainstream graphics hardware and virtual reality devices. CCS CONCEPTS • Computing methodologies → Ray tracing; Virtual reality.