Drop dead detect_background_color; sync docs with landed optimizations

- chroma.py: remove detect_background_color — orphaned since auto-detection
  goes through estimate_background_model -> _background_border_cluster;
  nothing in the repo calls it.
- settings.py: fix stale "Segmentation always stays fp32" comment
  (--precision now fans out to the BiRefNet models too).
- README: add a measured CPU performance section (9700X reference numbers,
  memory ceiling explanation, Zen 2 fallback guidance).
- docs/hair_gap_artifacts.md: record that the cross-check cost note is
  obsolete — reuse_as_seg returns the net model count to 2, bf16 and
  chunked attention absorb the rest.
- docs/green_screen_matting_workflow.md: add the 2026-07 additions to the
  architecture-evolution note.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

bgfilter/chroma.py

@@ -112,22 +112,6 @@ def _background_border_cluster(
     return full, share, agree
 
 
-def detect_background_color(
-    rgb: np.ndarray, settings: ChromaSettings | None = None
-) -> tuple[float, float, float]:
-    """Detect a single flat background colour from the image border.
-
-    Returns the colour as a 0..1 RGB triple. Raises RuntimeError (via
-    :func:`_background_border_cluster`) if the border is not dominated by one flat
-    colour, so callers fail loudly rather than matting against a wrong colour.
-    Pure: reads pixels only, with no matting side effects.
-    """
-    settings = settings or ChromaSettings()
-    rgb_f, lab = convert_color_spaces(rgb)
-    mask, _, _ = _background_border_cluster(lab, settings)
-    return tuple(float(x) for x in np.median(rgb_f[mask], axis=0))
-
-
 def estimate_background_model(
     rgb: np.ndarray,
     settings: ChromaSettings,

bgfilter/settings.py

@@ -129,10 +129,10 @@ class ModelSettings:
     matting_method: str = "vitmatte"
     fallback_to_chroma_alpha: bool = False
     # ViTMatte compute precision: "fp32" or "bf16". bf16 halves the matting
-    # model's activation memory (its full-resolution attention is the pipeline's
-    # memory peak) with visually identical alpha, but needs bf16-capable
-    # hardware (any modern GPU, or a CPU with AVX512-BF16/AMX) — otherwise it
-    # falls back to fp32 with a warning. Segmentation always stays fp32.
+    # model's activation memory with visually identical alpha, but needs
+    # bf16-capable hardware (any modern GPU, or a CPU with AVX512-BF16/AMX) —
+    # otherwise it falls back to fp32 with a warning. The BiRefNet models have
+    # their own precision fields; --precision sets all of them at once.
     precision: str = "fp32"
     # Query-chunked global attention (exact math, bitwise-identical output):
     # the VitDet backbone's 4 global blocks materialize an N^2 attention map —