NVIDIA Omniverse NuRec is a neural reconstruction pipeline for building high-fidelity 3D representations from multisensor data, used to reconstruct dynamic scenes from autonomous vehicle and robotics platforms into simulation-ready environments. It combines neural rendering techniques such as Gaussian splatting with GPU-accelerated rendering, but this fidelity comes with significant computational cost. At the start of the optimization effort, reconstructing even relatively short captures could take from over an hour to several hours depending on the scene and configuration. The team’s long-term goal is real-time reconstruction performance, where a 30-second capture can be reconstructed in approximately 30 seconds. To tackle these challenges, NVIDIA profiling and optimization tools were used, primarily NVIDIA Nsight Systems and NVIDIA Nsight Compute, to analyze the NuRec workload, identify bottlenecks, and iteratively optimize both the application-level workflow and the underlying CUDA kernels.