Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
This work addresses the need for clear and sharp car representations in urban scene simulators for autonomous driving applications, though it appears incremental as it builds on existing compositional neural scene graph methods.
The paper tackles the problem of blurring and artifacts when rotating cars in editable autonomous driving simulators by proposing a pipeline to learn car radiance fields from single-view and in-the-wild images, achieving competitive performance and enabling controllable appearance editing.
Compositional neural scene graph studies have shown that radiance fields can be an efficient tool in an editable autonomous driving simulator. However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulator. In this letter, we propose a pipeline for learning unconstrained images and building a dataset from processed images. To meet the requirements of the simulator, which demands that the vehicle maintain clarity when the perspective changes and that the contour remains sharp from the background to avoid artifacts when editing, we design a radiation field of the vehicle, a crucial part of the urban scene foreground. Through experiments, we demonstrate that our model achieves competitive performance compared to baselines. Using the datasets built from in-the-wild images, our method gradually presents a controllable appearance editing function. We will release the dataset and code on https://lty2226262.github.io/car-studio/ to facilitate further research in the field.