Neural-Sim: Learning to Generate Training Data with NeRF

Data augmentation: A comprehensive survey of modern approaches

“…Their approach aims to automatically find scene parameters for the simulation process that maximize the accuracy of trained model. More modern techniques such as NeuralSim [68] (Figure 8) employ neural radiance fields as implicit representations of simulation primitives instead of relying on explicitly modeled geometric primitives. The method has been designed to synthesize data for object detection tasks.…”

“…[56] generates synthetic data from primitive elements and utilizes reinforcement learning-based gradient approximation method known as REINFORCE algorithm [62] to estimate the gradients of the performance on the downstream task with respect to the data simulation and model parameters. [68]. The approach is a typical AutoML-based data synthesis models that employ a bi-level optimization scheme to fintune mode hypeparameters with the help of multiple feedback signals.…”

High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction

“…Rendering realistic images for virtual worlds is a key objective in many computer vision and graphics tasks (Huo and Yoon 2021;Xu et al 2022;Huang et al 2023;Li, Ngo, and Nagahara 2023), with applications in animation production (Dahlberg, Adler, and Newlin 2019), VR/AR world generation (Overbeck et al 2018), virtual dataset synthesis (Ge et al 2022), etc. One widely used technique for this purpose is Monte Carlo (MC) sampling (Seila 1982), which is highly versatile but typically requires a large number of samples to achieve accurate results.…”