Presentation
Spectral Prefiltering of Neural Fields
DescriptionNeural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include:
(1) We perform convolutional filtering in the input domain by analytically scaling
Fourier feature embeddings with the filter’s frequency response.
(2) This closed-form modulation generalizes beyond Gaussian filtering and
supports other parametric filters (Box and Lanczos) that are unseen at training time.
(3) We train the neural field using single-sample Monte Carlo estimates of the
filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering.
(1) We perform convolutional filtering in the input domain by analytically scaling
Fourier feature embeddings with the filter’s frequency response.
(2) This closed-form modulation generalizes beyond Gaussian filtering and
supports other parametric filters (Box and Lanczos) that are unseen at training time.
(3) We train the neural field using single-sample Monte Carlo estimates of the
filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering.
Authors
Event Type
Technical Papers
TimeTuesday, 16 December 20254:40pm - 4:51pm HKT
LocationMeeting Room S421, Level 4