Exploring Kernel Transformations for Implicit Neural Representations
This work provides a new approach for understanding and enhancing INRs, which are widely used for image representation, though it appears incremental as it builds on existing INR frameworks.
The paper tackles the problem of improving implicit neural representations (INRs) by exploring kernel transformations of input/output rather than modifying the model architecture, resulting in a simple scale-and-shift method that significantly boosts performance with negligible computational overhead.
Implicit neural representations (INRs), which leverage neural networks to represent signals by mapping coordinates to their corresponding attributes, have garnered significant attention. They are extensively utilized for image representation, with pixel coordinates as input and pixel values as output. In contrast to prior works focusing on investigating the effect of the model's inside components (activation function, for instance), this work pioneers the exploration of the effect of kernel transformation of input/output while keeping the model itself unchanged. A byproduct of our findings is a simple yet effective method that combines scale and shift to significantly boost INR with negligible computation overhead. Moreover, we present two perspectives, depth and normalization, to interpret the performance benefits caused by scale and shift transformation. Overall, our work provides a new avenue for future works to understand and improve INR through the lens of kernel transformation.