UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving
This addresses a critical bottleneck for autonomous driving systems that rely on multi-camera setups, offering a solution to enhance 3D scene reconstruction and perception, though it is incremental in advancing NeRF techniques for specific calibration issues.
The paper tackles the problem of applying Neural Radiance Fields (NeRF) to under-calibrated multi-camera systems in autonomous driving, which suffer from color inconsistencies and pose errors, and presents UC-NeRF, a method that achieves state-of-the-art performance in novel view synthesis and improves depth estimation in outdoor scenes.
Multi-camera setups find widespread use across various applications, such as autonomous driving, as they greatly expand sensing capabilities. Despite the fast development of Neural radiance field (NeRF) techniques and their wide applications in both indoor and outdoor scenes, applying NeRF to multi-camera systems remains very challenging. This is primarily due to the inherent under-calibration issues in multi-camera setup, including inconsistent imaging effects stemming from separately calibrated image signal processing units in diverse cameras, and system errors arising from mechanical vibrations during driving that affect relative camera poses. In this paper, we present UC-NeRF, a novel method tailored for novel view synthesis in under-calibrated multi-view camera systems. Firstly, we propose a layer-based color correction to rectify the color inconsistency in different image regions. Second, we propose virtual warping to generate more viewpoint-diverse but color-consistent virtual views for color correction and 3D recovery. Finally, a spatiotemporally constrained pose refinement is designed for more robust and accurate pose calibration in multi-camera systems. Our method not only achieves state-of-the-art performance of novel view synthesis in multi-camera setups, but also effectively facilitates depth estimation in large-scale outdoor scenes with the synthesized novel views.