光束法平差 (bundle adjustment) 是即時優化空間 3D 坐標的主要優化步驟，並且在視覺同步定位與地圖構建 (simultaneously localization and mapping) 中佔了很大一部分的執行時間。 儘管目前基於李文柏格-馬夸特 (Levenberg-Marquardt) 的演算法已普遍用於執行快速的光束法平差，但最近採用迭代且在原本硬體執行緩慢的基於高斯置信度傳播的光束法平差展現了其在新興計算平台 intelligence processing unit (IPU) 上快速和準確的潛力。 我們提出了一種新穎的架構來使用深度神經網路預測在高斯置信度傳播 (Gaussian belief propagation) 中傳遞的訊息。 該模型會提前生成標準高斯置信度中多次迭代後的訊息，以顯著減少所需循環計算的數量。此外，該程序藉由超參數的調整達到收斂，並避免了依賴不固定的阻尼因子來使高斯置信度傳播穩定。 與標準高斯置信度傳播相比，基於學習的方法在 GPU 加速下運行速度提高了 17.7 倍，並且有著相同的準確度水平。;Bundle adjustment (BA) is the major optimization step simultaneously refining 3D coordinates and accounts for a large portion of execution time in visual simultaneous localization and mapping (SLAM). While the Levenberg-Marquardt (LM) based algorithms have been commonly used for fast BA, recent solutions adopting iterative and originally slow Gaussian belief propagation (GBP) show its potential to be fast and accurate on emerging computation platforms, Intelligence Processing Unit (IPU). We propose a novel architecture to predict the message passing in GBP with deep neural networks. The model generates messages several iterations ahead to significantly reduce the number of required computation loops. Also, the process converges with hyperparameter tuning and avoids the dependency of an arbitrary damping factor for GBP to be stabilized. Compared with standard GBP, the learning-based approach achieves the same level of accuracy while running 17.7 times faster under GPU acceleration.
