Transaction-Science/open-standards
Watch
1
0
Fork
You've already forked open-standards
 0
Code Issues Pull requests Projects Releases 15 Packages Wiki Activity Actions

Restore JPEG-AI decoders (uv/hyper/hyper_scale/mcm/mans) wiped by the main reset #1

Merged
dcharlot merged 3 commits from recovery/jpegai-decoders into main 2026-07-08 04:47:44 -04:00
Conversation 0 Commits 3 Files changed 8 +905 -5
dcharlot commented 2026-07-08 04:45:54 -04:00
Owner
Copy link

These 5 byte-exact decoder PRs (#53/#54/#55 on the former GitHub canonical) were dropped from main during the migration to this Gitea. This branch restores them as a clean 3-commit fast-forward on top of #49. All validated: synthesis 58 dB, hyper 69 dB, hyper_scale + mANS entropy byte-exact.

These 5 byte-exact decoder PRs (#53/#54/#55 on the former GitHub canonical) were dropped from main during the migration to this Gitea. This branch restores them as a clean 3-commit fast-forward on top of #49. All validated: synthesis 58 dB, hyper 69 dB, hyper_scale + mANS entropy byte-exact.
Consolidated re-land of the JPEG-AI integer decode work that was rolled off main
(#51/#52 were merged then force-pushed out by a concurrent main rewrite), plus the
new hyper_scale_decoder. On top of the synthesis-Y decoder (#49):

  • decode_uv — chroma synthesis (model_uv): conv1(256->48) ‖ Slice(last96) ->
    Concat(144) -> conv2_t; TABs at full res; conv4_t(->8) -> DepthToSpace(CRD,2)
    -> 2-ch UV. 58.76 dB PSNR vs float ONNX.
  • decode_hyper — entropy hyper-prior decoder (common_modules): conv chain
    conv1(1x1)->conv2_t(4x4,up2)->ReLU6->conv3->ReLU6->conv4(->640). 69.55 dB SNR.
  • decode_hyper_scale — scale-index decoder (common_modules): a FULLY-INTEGER net
    (int64 symbols -> int32 scale indices). IntNet loader + exact integer conv +
    per-channel divide-by-2^n (truncation toward zero, not arithmetic shift) + QDQ
    clip + DepthToSpace(CRD,4) + abs + clip(0,3967). BYTE-EXACT (max|Δ| = 0) vs the
    onnx.reference evaluator — ORT rejects the model (no int64 Clip kernel), so the
    reference is the spec-compliant Python evaluator.

Pure i64 => byte-identical on every machine. Structural tests on the real weights
+ per-net calibration tests (feature-gated on assets). Header + module docs updated.

Co-authored-by: Transaction Science <[email protected]>
Co-authored-by: Claude Opus 4.8 <[email protected]>
Adds the 4-stage Multi-stage Context Model (common_modules/MCM) to the JPEG-AI
integer decode path. Each stage refines the entropy context, conditioned on the
stage's prior `p_i` and the accumulated decoded context `y[<i]`:

  • stage0 (no context): p0 -> conv1 -> ReLU -> conv2 -> ReLU -> conv3 -> y[0]
    (bias-free 1x1, width 160)
  • stage i>=1: cy = conv.1(conv.0(ctx));  Concat(cy, p_i) [->320]
    -> fusion.conv1 -> ReLU -> conv2 -> ReLU -> conv3 -> y[i]
    (conv.0 1x1 ctx_ch->160, conv.1 3x3 grouped-5 +bias; ctx = concat(y[i-1..0]))

Float nets -> Q16 PTQ (mcm_stage0/mcm_stage_n reuse the shared Weights loader +
conv path). Each stage validated independently against the float ONNX via ort:
SNR 73.86 / 68.94 / 61.98 / 61.18 dB (stages 0..3) — within the 16-bit PTQ.
Structural test on the real per-stage weights + tests/jpegai_mcm_calibration.rs.

Co-authored-by: Transaction Science <[email protected]>
Co-authored-by: Claude Opus 4.8 <[email protected]>
The entropy stage of the JPEG-AI decode path: a faithful pure-Rust port of the ISO
reference mANS decoder (cpp_exts/mans/decompressor.cpp). This is the central
non-neural piece — it turns the compressed bitstream into the latent symbols the
synthesis/hyper nets consume.

Mechanism (byte-for-byte with the reference):
  • two interleaved ANS states (state1/state2), advanced in a group-of-4
    inbound → flush → outbound schedule;
  • a rolling 64-bit window read MSB-first (read/flush), consumed backward through
    the byte buffer, with a sentinel-bit init (initBackward + initWithStates);
  • sgm path (main y-latent): a per-position sigma index selects one of 32
    precomputed transition tables; mask=false skips the position (value 0) without
    consuming the stream; the outbound/escape path (symbol == -bound) reads a
    sign + 3/16-bit magnitude for out-of-range values;
  • fac path (z hyper-latent): a per-channel cumulative CDF builds the row table
    (transitionsZPreprocess), symbol == MAX_Z(63) escapes to a raw 6-bit value.

State threads across calls, so one MansDecoder decodes a whole stream.

Validated BYTE-EXACT against the ISO reference (the golden was produced by the
reference `ans.so`): decode_sgm 40960/40960 exact on the real SORP stream (160
calls, 703 coded symbols, two states, escapes), decode_factorize 128/128 exact on
an oracle encode→decode roundtrip. Tests feature-gated on the fixtures.

Co-authored-by: Transaction Science <[email protected]>
Co-authored-by: Claude Opus 4.8 <[email protected]>
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
Transaction-Science/open-standards!1
No description provided.