diff --git a/image_analysis/geom_refinement/PostRefine.cpp b/image_analysis/geom_refinement/PostRefine.cpp
index 21948c46..25f23ef1 100644
--- a/image_analysis/geom_refinement/PostRefine.cpp
+++ b/image_analysis/geom_refinement/PostRefine.cpp
@@ -136,8 +136,14 @@ PostRefineResult PostRefineRotationGeometry(const std::vector<IntegrationOutcome
         // reflections copies the whole thing every time it doubles - several gigabytes of pure
         // copying - and the counts are cheap to take. Each outcome then owns a slice, so the fill
         // runs on all threads and lands in the order the serial loop produced.
+        // Both passes below are chunked over OUTCOMES but their cost is in the reflections inside them,
+        // tens of thousands per frame, so the worker count has to come from the reflection count. Asked
+        // about the outcomes instead, ThreadsForWork sees a frame count against its 32768-per-thread
+        // floor and answers 1 - which ran the whole gather on one thread on every dataset in the test
+        // set. RotationScaleMerge::Ingest already asks the same question the right way round.
+        const size_t gather_threads = ThreadsForWork(n_integrated, nthreads);
         std::vector<size_t> pts_offset(n_out + 1, 0);
-        ParallelChunks(n_out, ThreadsForWork(static_cast<size_t>(n_out), nthreads), [&](int lo, int hi) {
+        ParallelChunks(n_out, gather_threads, [&](int lo, int hi) {
             for (int o = lo; o < hi; o++) {
                 size_t keep = 0;
                 for (const auto &r : outcomes[o].reflections)
@@ -151,7 +157,7 @@ PostRefineResult PostRefineRotationGeometry(const std::vector<IntegrationOutcome
             pts_offset[o + 1] += pts_offset[o];
 
         std::vector<Partial> pts(pts_offset[n_out]);
-        ParallelChunks(n_out, ThreadsForWork(static_cast<size_t>(n_out), nthreads), [&](int lo, int hi) {
+        ParallelChunks(n_out, gather_threads, [&](int lo, int hi) {
             for (int o = lo; o < hi; o++) {
                 size_t at = pts_offset[o];
                 for (const auto &r : outcomes[o].reflections) {