BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
This addresses a practical issue for real-world applications of NeRF where image quality is degraded, though it is an incremental improvement by extending NeRF to handle blur and pose inaccuracies.
The paper tackles the problem of 3D reconstruction and novel view synthesis with motion-blurred images and inaccurate camera poses in Neural Radiance Fields (NeRF), achieving superior performance over prior works on synthetic and real datasets.
Neural Radiance Fields (NeRF) have received considerable attention recently, due to its impressive capability in photo-realistic 3D reconstruction and novel view synthesis, given a set of posed camera images. Earlier work usually assumes the input images are of good quality. However, image degradation (e.g. image motion blur in low-light conditions) can easily happen in real-world scenarios, which would further affect the rendering quality of NeRF. In this paper, we present a novel bundle adjusted deblur Neural Radiance Fields (BAD-NeRF), which can be robust to severe motion blurred images and inaccurate camera poses. Our approach models the physical image formation process of a motion blurred image, and jointly learns the parameters of NeRF and recovers the camera motion trajectories during exposure time. In experiments, we show that by directly modeling the real physical image formation process, BAD-NeRF achieves superior performance over prior works on both synthetic and real datasets. Code and data are available at https://github.com/WU-CVGL/BAD-NeRF.