URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fields
This addresses the limitation of requiring strict sequential data for rolling shutter correction in NeRF, making it more applicable for real-world scenarios.
The paper tackles the problem of low-quality images and inaccurate camera poses in neural radiance fields (NeRF) due to rolling shutter effects, by proposing a method that recovers physical image formation using unordered images, resulting in improved 3D reconstruction without requiring sequential video input.
We propose a novel rolling shutter bundle adjustment method for neural radiance fields (NeRF), which utilizes the unordered rolling shutter (RS) images to obtain the implicit 3D representation. Existing NeRF methods suffer from low-quality images and inaccurate initial camera poses due to the RS effect in the image, whereas, the previous method that incorporates the RS into NeRF requires strict sequential data input, limiting its widespread applicability. In constant, our method recovers the physical formation of RS images by estimating camera poses and velocities, thereby removing the input constraints on sequential data. Moreover, we adopt a coarse-to-fine training strategy, in which the RS epipolar constraints of the pairwise frames in the scene graph are used to detect the camera poses that fall into local minima. The poses detected as outliers are corrected by the interpolation method with neighboring poses. The experimental results validate the effectiveness of our method over state-of-the-art works and demonstrate that the reconstruction of 3D representations is not constrained by the requirement of video sequence input.