feat: chunked cpfind for large panoramas (>20 images)

Splits large image sets into overlapping chunks of 20 images
(5 image overlap between chunks). Each chunk runs cpfind + cpclean
independently, then CPs are merged with remapped global indices.

Avoids O(n^2) explosion:
- 80 images monolithic: cpfind ~30min + cpclean ~70min = ~100min
- 80 images in 4 chunks of 20: ~4x(2min + 0.5min) = ~10min estimated

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

pipeline/panorama_pipeline.py

@@ -280,11 +280,15 @@ def build_pto(pto_path, img_paths, azs, els, img_w, img_h, fov, ref_idx=None):
 # ============================================================
 
 def run_pipeline(work_dir, clahe_images, original_images, azs, els,
-                 img_w, img_h, fov, output_name, blender="auto", camera=None):
+                 img_w, img_h, fov, output_name, blender="auto", camera=None,
+                 chunk_size=20, chunk_overlap=5):
     """Full pipeline: cpfind(CLAHE) -> swap(originals) -> optimize(geo) -> nona -> blend.
 
+    For large panoramas (>chunk_size images), cpfind runs on overlapping chunks
+    to avoid O(n^2) explosion in cpfind --multirow and cpclean.
+
     Blender selection:
-      - auto: enblend for NavCam (better vignette/horizon), verdandi for Mastcam-Z (no seam overexposure)
+      - auto: enblend for NavCam, verdandi for Mastcam-Z
       - enblend: force enblend --pre-assemble
       - verdandi: force verdandi
     """
@@ -296,35 +300,113 @@ def run_pipeline(work_dir, clahe_images, original_images, azs, els,
             blender = "enblend"
 
     timings = {}
+    n_images = len(clahe_images)
 
-    # Build CLAHE PTO
+    # Build full CLAHE PTO (needed for final assembly)
     pto_clahe = os.path.join(work_dir, f"{output_name}_clahe.pto")
     build_pto(pto_clahe, clahe_images, azs, els, img_w, img_h, fov)
 
-    # cpfind on CLAHE images
-    print("  cpfind...", flush=True)
-    t0 = time.time()
-    r = run_hugin("cpfind",
-        f"--multirow --celeste "
-        f"--sieve1width 20 --sieve1height 20 --sieve1size 1000 "
-        f"--sieve2width 10 --sieve2height 10 --sieve2size 5 "
-        f"--minmatches 3 --ransaciter 2000 --ransacdist 50 "
-        f'-o "{pto_clahe}" "{pto_clahe}"',
-        cwd=work_dir)
-    timings["cpfind"] = time.time() - t0
-    for line in r.stdout.split("\n"):
-        if "Found" in line:
-            print(f"    {line.strip()}")
+    if n_images <= chunk_size:
+        # Small panorama: run cpfind on all images at once
+        print(f"  cpfind ({n_images} images)...", flush=True)
+        t0 = time.time()
+        r = run_hugin("cpfind",
+            f"--multirow --celeste "
+            f"--sieve1width 20 --sieve1height 20 --sieve1size 1000 "
+            f"--sieve2width 10 --sieve2height 10 --sieve2size 5 "
+            f"--minmatches 3 --ransaciter 2000 --ransacdist 50 "
+            f'-o "{pto_clahe}" "{pto_clahe}"',
+            cwd=work_dir)
+        timings["cpfind"] = time.time() - t0
+        for line in r.stdout.split("\n"):
+            if "Found" in line:
+                print(f"    {line.strip()}")
 
-    # cpclean
-    print("  cpclean...", flush=True)
-    t0 = time.time()
-    run_hugin("cpclean", f'-o "{pto_clahe}" "{pto_clahe}"', cwd=work_dir)
-    timings["cpclean"] = time.time() - t0
+        # cpclean
+        print("  cpclean...", flush=True)
+        t0 = time.time()
+        run_hugin("cpclean", f'-o "{pto_clahe}" "{pto_clahe}"', cwd=work_dir)
+        timings["cpclean"] = time.time() - t0
 
+    else:
+        # Large panorama: chunked cpfind strategy
+        # Split into overlapping chunks, cpfind each, merge CPs
+        step = chunk_size - chunk_overlap
+        chunks = []
+        i = 0
+        while i < n_images:
+            end = min(i + chunk_size, n_images)
+            chunks.append((i, end))
+            if end >= n_images:
+                break
+            i += step
+
+        print(f"  Chunked cpfind: {n_images} images -> {len(chunks)} chunks of ~{chunk_size} "
+              f"(overlap={chunk_overlap})", flush=True)
+
+        all_cp_lines = []
+        t0_total = time.time()
+
+        for chunk_idx, (start, end) in enumerate(chunks):
+            chunk_clahe = clahe_images[start:end]
+            chunk_azs = azs[start:end]
+            chunk_els = els[start:end]
+
+            # Build chunk PTO
+            chunk_pto = os.path.join(work_dir, f"{output_name}_chunk{chunk_idx}.pto")
+            build_pto(chunk_pto, chunk_clahe, chunk_azs, chunk_els, img_w, img_h, fov)
+
+            # cpfind on chunk
+            t0 = time.time()
+            r = run_hugin("cpfind",
+                f"--multirow --celeste "
+                f"--sieve1width 20 --sieve1height 20 --sieve1size 1000 "
+                f"--sieve2width 10 --sieve2height 10 --sieve2size 5 "
+                f"--minmatches 3 --ransaciter 2000 --ransacdist 50 "
+                f'-o "{chunk_pto}" "{chunk_pto}"',
+                cwd=work_dir)
+            cp_time = time.time() - t0
+
+            # cpclean on chunk
+            run_hugin("cpclean", f'-o "{chunk_pto}" "{chunk_pto}"', cwd=work_dir)
+
+            # Read CPs and remap indices to global
+            with open(chunk_pto) as f:
+                for line in f:
+                    if line.startswith("c "):
+                        # Remap local image indices to global
+                        parts = line.split()
+                        new_parts = []
+                        for p in parts:
+                            if p.startswith("n") and not p.startswith("N"):
+                                local_idx = int(p[1:])
+                                new_parts.append(f"n{start + local_idx}")
+                            elif p.startswith("N"):
+                                local_idx = int(p[1:])
+                                new_parts.append(f"N{start + local_idx}")
+                            else:
+                                new_parts.append(p)
+                        all_cp_lines.append(" ".join(new_parts) + "\n")
+
+            # Cleanup chunk PTO
+            os.remove(chunk_pto)
+
+            chunk_cps = len([l for l in all_cp_lines])  # running total
+            print(f"    Chunk {chunk_idx+1}/{len(chunks)} "
+                  f"(imgs {start}-{end-1}): {cp_time:.0f}s, "
+                  f"total CPs so far: {len(all_cp_lines)}", flush=True)
+
+        timings["cpfind"] = time.time() - t0_total
+        timings["cpclean"] = 0  # included in per-chunk processing
+
+        # Write CPs back to the full CLAHE PTO
+        with open(pto_clahe, "a") as f:
+            f.writelines(all_cp_lines)
+
+    # Count final CPs
     with open(pto_clahe) as f:
         cp_lines = [l for l in f if l.startswith("c ")]
-    print(f"  CPs: {len(cp_lines)}")
+    print(f"  Total CPs: {len(cp_lines)}")
 
     if len(cp_lines) < 5:
         print("  ERROR: Not enough control points")
@@ -336,7 +418,7 @@ def run_pipeline(work_dir, clahe_images, original_images, azs, els,
     with open(pto_render, "a") as f:
         f.writelines(cp_lines)
 
-    # Geometry-only optimization (NO -m, NO -a to avoid d/e distortion)
+    # Geometry-only optimization (NO -m)
     print("  autooptimiser (geo only)...", flush=True)
     t0 = time.time()
     run_hugin("autooptimiser", f'-a -l -s -o "{pto_render}" "{pto_render}"', cwd=work_dir)