gsplat op• Data kinds: none → table (an op determined by its arguments alone — it takes no image or data input)
• Call: import fullseye as fs; fs.ledger.gs_read_file(path, *, min_opacity: 'float' = 0.0) -> 'dict' (to call the implementation directly, import gsplatnp; gsplatnp.gs_read_file(path, *, min_opacity: 'float' = 0.0) -> 'dict'; from the registry, opsdrive.get("gs_read_file"))
Reads a 3D Gaussian Splatting file and returns the Gaussians' centers, colors, opacities, scales and orientations.
Supported: INRIA-format .ply (x, y, z, f_dc_0..2, opacity (logit), scale_0..2 (log), rot_0..3 (wxyz); the output of gsplat_train_native is also this) and .splat (32 bytes each: position 3×f32, scale 3×f32, RGBA 4×u8, rotation 4×u8 (wxyz, (q·128)+128)).
Args:
path: the file.
min_opacity: drop Gaussians with opacity below this (0 keeps all).
Returns:
{"xyz" (N,3), "rgb" (N,3) [0,1], "opacity" (N,) [0,1], "scale" (N,3)(実寸、exp 済み), "rot" (N,4) wxyz 単位四元数, "n_total", "format"}. Colour is only the 0th-order spherical harmonic (higher orders that vary with viewpoint are discarded).
• 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.
• gallery_drive_world_io — py -3.11 examples/gallery_drive_world_io.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
gsplat)gs_from_world · gs_update · gs_render · gs_render_fn
*Provenance: gsplatnp.py — DRIVE 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.