Landscape record (not normative). Learned coding is moving into 3D: JPEG Pleno
point-cloud coding is finalized and reuses JPEG AI for its colour attributes, and
Gaussian Splat Coding is under standardization applying Neural Network Coding to
splat parameters. Both inherit the cross-platform non-determinism of learned 2D
codecs.
WAI already decodes one 3D representation byte-exactly — wai.splat.int_codec, a
pure-i64 Gaussian-splat attribute codec at the decode-equivalence tier
(splat-equivalence: the attribute tensor is byte-identical everywhere). The note
records that the determinism contract + reconstruction binding generalize to
decoded 3D representations exactly as to pixels, and is honest about scope: WAI's
splat codec is WAI-native, NOT the ISO point-cloud bitstream — the shared thing is
the problem and the approach. Because JPEG-Pleno PCC reuses JPEG AI for colour, the
byte-exact JPEG-AI decode WAI has is a component a future wai.pointcloud.* path
could build on. Recorded as the natural next capability, not a separate track.
Framed self-referentially; standards named as standards, no comparisons.
Co-Authored-By: Claude Opus 4.8 <[email protected]>