synth op• Data kinds: none → volseq (an op determined by its arguments alone — it takes no image or data input)
• Call: import fullseye as fs; fs.ledger.volseq_synth_dividing(shape=(24, 32, 32), n_frames: 'int' = 24, split_frame: 'int' = 8, speed: 'float' = 0.5, sigma: 'float' = 2.5, axis: 'int' = 3, noise: 'float' = 0.0, seed: 'int' = 0) -> 'np.ndarray' (to call the implementation directly, import live4d; live4d.volseq_synth_dividing(shape=(24, 32, 32), n_frames: 'int' = 24, split_frame: 'int' = 8, speed: 'float' = 0.5, sigma: 'float' = 2.5, axis: 'int' = 3, noise: 'float' = 0.0, seed: 'int' = 0) -> 'np.ndarray'; from the registry, opslive4d.get("volseq_synth_dividing"))
> This operator's description has not been translated yet. The original text follows as it is.
既知の速さで二つに分かれる塊の体積時系列 `(T, Z, Y, X)(volseq`)。
`split_frame までは中心に 1 つのガウス塊(標準偏差 sigma)、それ以降は 2 つの塊が axis`
(1 = z, 2 = y, 3 = x)に沿って `±speed · (t − split_frame)` voxel ずつ離れる(細胞分裂の最小モデル)。
真値 = 中心の位置なので、流れ(`vol_flow_3d)は ±speed` の並進、軌跡は直線になるはず。
>>> s = volseq_synth_dividing((16, 24, 24), n_frames=12, split_frame=4, speed=0.5)
>>> s.shape
(12, 16, 24, 24)
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
• The canonical algorithm (author, year) and its uses are named in the family usage guide above.
• poc_live4d — py -3.11 examples/poc_live4d.py
volseq as input)volseq_mip_video · volseq_cut_video · volseq_speed · volseq_pathline_render · volseq_pathline_orbit · volseq_interpolate_flow · volseq_magnify_motion · volseq_render_orbit
synth)*Provenance: live4d.py — LIVE4D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.