The 3D reconstruction pipeline uses the Bundle Adjustment algorithm to refine the camera and point parameters. The Bundle Adjustment algorithm is a compute-intensive algorithm, and many researchers have improved its p...The 3D reconstruction pipeline uses the Bundle Adjustment algorithm to refine the camera and point parameters. The Bundle Adjustment algorithm is a compute-intensive algorithm, and many researchers have improved its performance by implementing the algorithm on GPUs. In the previous research work, “Improving Accuracy and Computational Burden of Bundle Adjustment Algorithm using GPUs,” the authors demonstrated first the Bundle Adjustment algorithmic performance improvement by reducing the mean square error using an additional radial distorting parameter and explicitly computed analytical derivatives and reducing the computational burden of the Bundle Adjustment algorithm using GPUs. The naïve implementation of the CUDA code, a speedup of 10× for the largest dataset of 13,678 cameras, 4,455,747 points, and 28,975,571 projections was achieved. In this paper, we present the optimization of the Bundle Adjustment algorithm CUDA code on GPUs to achieve higher speedup. We propose a new data memory layout for the parameters in the Bundle Adjustment algorithm, resulting in contiguous memory access. We demonstrate that it improves the memory throughput on the GPUs, thereby improving the overall performance. We also demonstrate an increase in the computational throughput of the algorithm by optimizing the CUDA kernels to utilize the GPU resources effectively. A comparative performance study of explicitly computing an algorithm parameter versus using the Jacobians instead is presented. In the previous work, the Bundle Adjustment algorithm failed to converge for certain datasets due to several block matrices of the cameras in the augmented normal equation, resulting in rank-deficient matrices. In this work, we identify the cameras that cause rank-deficient matrices and preprocess the datasets to ensure the convergence of the BA algorithm. Our optimized CUDA implementation achieves convergence of the Bundle Adjustment algorithm in around 22 seconds for the largest dataset compared to 654 seconds for the sequential implementation, resulting in a speedup of 30×. Our optimized CUDA implementation presented in this paper has achieved a 3× speedup for the largest dataset compared to the previous naïve CUDA implementation.展开更多
Bundle adjustment is a camera and point refinement technique in a 3D scene reconstruction pipeline. The camera parameters and the 3D points are refined by minimizing the difference between computed projection and obse...Bundle adjustment is a camera and point refinement technique in a 3D scene reconstruction pipeline. The camera parameters and the 3D points are refined by minimizing the difference between computed projection and observed projection of the image points formulated as a non-linear least-square problem. Levenberg-Marquardt method is used to solve the non-linear least-square problem. Solving the non-linear least-square problem is computationally expensive, proportional to the number of cameras, points, and projections. In this paper, we implement the Bundle Adjustment (BA) algorithm and analyze techniques to improve algorithmic performance by reducing the mean square error. We investigate using an additional radial distortion camera parameter in the BA algorithm and demonstrate better convergence of the mean square error. We also demonstrate the use of explicitly computed analytical derivatives. In addition, we implement the BA algorithm on GPUs using the CUDA parallel programming model to reduce the computational time burden of the BA algorithm. CUDA Streams, atomic operations, and cuBLAS library in the CUDA programming model are proposed, implemented, and demonstrated to improve the performance of the BA algorithm. Our implementation has demonstrated better convergence of the BA algorithm and achieved a speedup of up to 16× on the use of the BA algorithm on various datasets.展开更多
文摘The 3D reconstruction pipeline uses the Bundle Adjustment algorithm to refine the camera and point parameters. The Bundle Adjustment algorithm is a compute-intensive algorithm, and many researchers have improved its performance by implementing the algorithm on GPUs. In the previous research work, “Improving Accuracy and Computational Burden of Bundle Adjustment Algorithm using GPUs,” the authors demonstrated first the Bundle Adjustment algorithmic performance improvement by reducing the mean square error using an additional radial distorting parameter and explicitly computed analytical derivatives and reducing the computational burden of the Bundle Adjustment algorithm using GPUs. The naïve implementation of the CUDA code, a speedup of 10× for the largest dataset of 13,678 cameras, 4,455,747 points, and 28,975,571 projections was achieved. In this paper, we present the optimization of the Bundle Adjustment algorithm CUDA code on GPUs to achieve higher speedup. We propose a new data memory layout for the parameters in the Bundle Adjustment algorithm, resulting in contiguous memory access. We demonstrate that it improves the memory throughput on the GPUs, thereby improving the overall performance. We also demonstrate an increase in the computational throughput of the algorithm by optimizing the CUDA kernels to utilize the GPU resources effectively. A comparative performance study of explicitly computing an algorithm parameter versus using the Jacobians instead is presented. In the previous work, the Bundle Adjustment algorithm failed to converge for certain datasets due to several block matrices of the cameras in the augmented normal equation, resulting in rank-deficient matrices. In this work, we identify the cameras that cause rank-deficient matrices and preprocess the datasets to ensure the convergence of the BA algorithm. Our optimized CUDA implementation achieves convergence of the Bundle Adjustment algorithm in around 22 seconds for the largest dataset compared to 654 seconds for the sequential implementation, resulting in a speedup of 30×. Our optimized CUDA implementation presented in this paper has achieved a 3× speedup for the largest dataset compared to the previous naïve CUDA implementation.
文摘Bundle adjustment is a camera and point refinement technique in a 3D scene reconstruction pipeline. The camera parameters and the 3D points are refined by minimizing the difference between computed projection and observed projection of the image points formulated as a non-linear least-square problem. Levenberg-Marquardt method is used to solve the non-linear least-square problem. Solving the non-linear least-square problem is computationally expensive, proportional to the number of cameras, points, and projections. In this paper, we implement the Bundle Adjustment (BA) algorithm and analyze techniques to improve algorithmic performance by reducing the mean square error. We investigate using an additional radial distortion camera parameter in the BA algorithm and demonstrate better convergence of the mean square error. We also demonstrate the use of explicitly computed analytical derivatives. In addition, we implement the BA algorithm on GPUs using the CUDA parallel programming model to reduce the computational time burden of the BA algorithm. CUDA Streams, atomic operations, and cuBLAS library in the CUDA programming model are proposed, implemented, and demonstrated to improve the performance of the BA algorithm. Our implementation has demonstrated better convergence of the BA algorithm and achieved a speedup of up to 16× on the use of the BA algorithm on various datasets.
