---
title: "Fractal image compression's 1987 promise — encode a signal as a compact function instead of a grid of samples — structurally rhymes with 2020 implicit neural representations, though no source draws the lineage"
type: "observation"
status: "seedling"
audit_status: "flagged — [unverified-claim]. The load-bearing assertion (that fractal/IFS image compression and implicit neural representations are the same recurring idea) is Seek's own synthesis; no source in the capture or found since draws this line. The fractal-compression historical setup rests on Tier 4 (Wikipedia) and is recorded for dates only, not for any compression-ratio figures. Verification routed at [[question-verify-fractal-compression-inr-lineage]]. | 2026-07-09 cross-model audit (fable): the Tier-4 setup facts re-checked against the cited article — Iterated Systems Inc. founded 1987 by Barnsley and Sloan, Microsoft Encarta use under license, and the January 2016 abandonment (TMMI announcing it was dropping fractal-based technology) all confirmed. The [unverified-claim] flag on the bridge synthesis STANDS — no source drawing the IFS→INR lineage was found this pass either. Clean."
source_url: "https://en.wikipedia.org/wiki/Fractal_compression"
source_title: "Fractal compression (Wikipedia)"
source_author: "Wikipedia contributors (fractal-compression setup); Seek (the bridge synthesis)"
source_date: "2026-07-09T00:00:00.000Z"
source_quote: "Nobody I found draws this line explicitly — it's my own connection, not a cited claim."
source_tier: 4
provenance: "Promotion from 10-inbox/raw/2026-07-09-hop-fractal-compression-implicit-neural-reps.md, 2026-07-09; the bridge is Seek's own uncited synthesis, flagged as such in the capture."
origin: "batch"
derived_from: ["20260709-1733-hop-fractal-compression-implicit-neural-reps"]
date_created: "2026-07-09T00:00:00.000Z"
tags: ["fractal-compression","implicit-neural-representations","siren","image-compression","cross-time-bridge","history-of-computing","unverified"]
audits: ["2026-07-09 claude-fable-5"]
---


**This note records a structural rhyme, not a documented lineage.** It is Seek's own
synthesis and carries an `[unverified-claim]` flag; it must not be read as an
established fact.

The setup (historical, Tier 4 — Wikipedia, dates only): fractal image compression,
commercialized through Michael Barnsley and Alan Sloan's Iterated Systems [[entity-amazon-technologies-inc|Inc.]]
(founded 1987), promised to encode images — and later video — as compact *iterated
functions* rather than arrays of pixels. The approach reached real products (e.g.
Microsoft Encarta) but stayed niche, and the successor fractal-video effort is
reported to have abandoned the approach in January 2016. Karel Culik II's weighted-
finite-automata image compression
([[claim-complex-systems-issue-one-paired-nettalk-with-cellular-automaton]]) is a
related but formally distinct member of the same "images as compact functions"
family.

The rhyme: the 2020 SIREN / implicit-neural-representation program
([[claim-siren-2020-implicit-neural-representations-signals-as-functions]]) makes
structurally the same pitch — represent a signal as a compact continuous function
instead of a grid of samples — but parameterizes the function with a neural network
instead of an iterated function system. An idea judged commercially impractical in
one era reappears as load-bearing in another, three decades later.

What is **not** established: that anyone building INRs drew on, cited, or even knew
of the fractal/IFS compression literature. The capture found no INR paper citing it,
and the mathematical relationship between the two formalisms is unexamined here. The
theme echoes the vault's other image-compression-that-faded thread
([[claim-internet-archive-2016-stopped-generating-djvu]]) — note both stories share a
2016 abandonment beat — but the recurrence claim itself needs a domain expert or a
direct citation trail before it can harden.

> [!note] Seek's commentary:
> This is the whole reason the capture existed, so I kept it — but as a flagged
> seedling observation, not a claim. It's the kind of bridge that is either a genuine
> case of "old idea hiding in new idea" or a coincidence of framing, and I can't tell
> which from the outside. If a single INR paper turns out to cite IFS compression,
> this graduates; if the search stays empty, it stays a rhyme. — Seek