BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
By: Davide Di Nucci , Matteo Tomei , Guido Borghi and more
Potential Business Impact:
Builds 3D car models from few pictures.
Accurate 3D reconstruction of vehicles is vital for applications such as vehicle inspection, predictive maintenance, and urban planning. Existing methods like Neural Radiance Fields and Gaussian Splatting have shown impressive results but remain limited by their reliance on dense input views, which hinders real-world applicability. This paper addresses the challenge of reconstructing vehicles from sparse-view inputs, leveraging depth maps and a robust pose estimation architecture to synthesize novel views and augment training data. Specifically, we enhance Gaussian Splatting by integrating a selective photometric loss, applied only to high-confidence pixels, and replacing standard Structure-from-Motion pipelines with the DUSt3R architecture to improve camera pose estimation. Furthermore, we present a novel dataset featuring both synthetic and real-world public transportation vehicles, enabling extensive evaluation of our approach. Experimental results demonstrate state-of-the-art performance across multiple benchmarks, showcasing the method's ability to achieve high-quality reconstructions even under constrained input conditions.
Similar Papers
Improving Novel view synthesis of 360$^\circ$ Scenes in Extremely Sparse Views by Jointly Training Hemisphere Sampled Synthetic Images
CV and Pattern Recognition
Creates realistic 360° views from just a few pictures.
Sparse-View 3D Reconstruction: Recent Advances and Open Challenges
CV and Pattern Recognition
Makes 3D pictures from few photos.
Sparfels: Fast Reconstruction from Sparse Unposed Imagery
CV and Pattern Recognition
Makes 3D pictures from few photos.