Summary · Chapter 1

Signals and how to store them

Signal: a function f : Ω → ℝD from image locations to D numbers (1 for grey, 3 for colour, 384 for the feature maps in this work).

FamilyStoresRead-outExample
ExplicitValues at grid pointsLookupPixels; a 16×16 or 32×32 feature grid
Implicit (neural field)Weights of a functionEvaluate the network at xNeRF, SIREN
HybridSpatially meaningful partsSimple rule or tiny networkInstant-NGP; sets of primitives such as Gaussians

Two questions for any method: how is it read at a location; how are its parameters found (per-signal optimisation, or amortised: one pass of a network trained on many inputs).

Trade-offs: explicit costs memory that grows with resolution and exists only at samples (values between them come from a chosen rule); implicit is defined everywhere but needs per-signal fitting and has opaque weights; hybrids keep interpretable parts with a cheap read-out.

Key numbers: 16×16 × 384 = 98,304 stored numbers; 32×32 × 384 = 393,216. On a 256-pixel image each 16×16 cell covers 16 by 16 pixels. 64 Gaussians with 384 features each store about a quarter of the 16×16 grid's numbers and can be read anywhere.

MethodRead-outParameters found by
Pixel gridLookupMeasurement
NeRF, SIRENNetwork at xOptimisation per signal
Instant-NGPGrid lookup + tiny networkOptimisation per signal
This modelSimple rule over GaussiansPlacement amortised by a network

Defence answer: “It is not just an implicit neural representation. It is read by a simple rule over explicit parts that each sit somewhere in the image, and those parts are placed by one pass of a trained network, not fitted per image.”

Source: Xie et al., Neural Fields in Visual Computing and Beyond (2022).