SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
This addresses the challenge of motion blur in 3D scene reconstruction for applications like view synthesis, but it appears incremental as it builds on existing NeRF methods.
The paper tackles the problem of motion blur in neural radiance fields (NeRF) by proposing SMURF, which models continuous camera motion to handle blurry input images, achieving state-of-the-art performance on benchmark datasets.
Neural radiance fields (NeRF) has attracted considerable attention for their exceptional ability in synthesizing novel views with high fidelity. However, the presence of motion blur, resulting from slight camera movements during extended shutter exposures, poses a significant challenge, potentially compromising the quality of the reconstructed 3D scenes. To effectively handle this issue, we propose sequential motion understanding radiance fields (SMURF), a novel approach that models continuous camera motion and leverages the explicit volumetric representation method for robustness to motion-blurred input images. The core idea of the SMURF is continuous motion blurring kernel (CMBK), a module designed to model a continuous camera movements for processing blurry inputs. Our model is evaluated against benchmark datasets and demonstrates state-of-the-art performance both quantitatively and qualitatively.