terrain op• Data kinds: table × table × matrix × matrix × table → table
• Call: import fullseye as fs; fs.ledger.world_materials(world: 'dict', view: 'dict', pose, K, m: 'dict') -> 'dict' (to call the implementation directly, import driveterrain; driveterrain.world_materials(world: 'dict', view: 'dict', pose, K, m: 'dict') -> 'dict'; from the registry, opsdrive.get("world_materials"))
Applies road-surface materials pixel by pixel to the rendering view (from world_camera, including "shade").
Road-surface (label 0) and terrain (10) pixels have their material re-evaluated in world coordinates: asphalt grain (Perlin, 8 cycles/m), colour unevenness of grass, stains (dark patches, label stays 0), puddles (sky reflection, label 11). White lines and crosswalks (9, 12) are blended into the road colour by the wear rate wear (label unchanged, kept in the ground truth "wear"). The strength of the puddle reflection (0.1 to 0.9, Perlin 1.5 cycles/m) is the ground truth "refl". Returns {"color", "label", "puddle", "refl", "stain", "wear", "xyz"}.
Empty input (world an empty dict) raises ValueError.
• 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_world_terrain — py -3.11 examples/poc_world_terrain.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
terrain)perlin2 · fbm_params · fbm_height · fbm_gradient · radial_periodogram · spectral_slope · course_distance · terrain_params
*Provenance: driveterrain.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.