Processing Load Allocation of On-Board Multi-User Detection for Payload-Constrained Satellite Networks

The rapid advance of mega-constellation facilitates the booming of direct-to-satellite massive access, where multi-user detection is critical to alleviate the induced inter-user interference. While centralized implementation of on-board detection induces unaffordable complexity for a single satellite, this paper proposes to allocate the processing load among cooperative satellites for finest exploitation of distributed processing power. Observing the inherent disparities among users, we first excavate the closed-form trade-offs between achievable sum-rate and the processing load corresponding to the satellite-user matchings, which leads to a system sum-rate maximization problem under stringent payload constraints. To address the non-trivial integer matching, we develop a quadratic transformation to the original problem, and prove it an equivalent conversion. The problem is further simplified into a series of subproblems employing successive lower bound approximation which obtains polynomial-time complexity and converges within a few iterations. Numerical results show remarkably complexity reduction compared with centralized processing, as well as around 20\% sum-rate gain compared with other allocation methods.

Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by consumer-level devices like smartphones, due to practical complicating factors such as thin structures, non-ideal rectification, camera module inconsistencies and various hard-case scenes. In this paper, we propose a set of innovative designs to tackle the problem of practical stereo matching: 1) to better recover fine depth details, we design a hierarchical network with recurrent refinement to update disparities in a coarse-to-fine manner, as well as a stacked cascaded architecture for inference; 2) we propose an adaptive group correlation layer to mitigate the impact of erroneous rectification; 3) we introduce a new synthetic dataset with special attention to difficult cases for better generalizing to real-world scenes. Our results not only rank 1st on both Middlebury and ETH3D benchmarks, outperforming existing state-of-the-art methods by a notable margin, but also exhibit high-quality details for real-life photos, which clearly demonstrates the efficacy of our contributions.