{"name":"haci","repo":"RenderBear/haci","url":"https://midorreal.com/project/renderbear-haci","repository":"https://github.com/RenderBear/haci","description":"Harmonic Contour Integration - A compact, fully distributed algorithm that extracts edges from RGB images","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/RenderBear/haci","checked":"21 Nov 2026"},"language":{"value":"Python","source":"https://github.com/RenderBear/haci","checked":"21 Nov 2026"},"releases":{"value":"0","source":"https://github.com/RenderBear/haci/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/RenderBear/haci/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/RenderBear/haci","checked":"21 Nov 2026"}},"stars":22.0,"writeup":{"what_it_is":"HaCI (Harmonic Contour Integration) is an edge detection algorithm for RGB images. It runs in four stages: pixel-level harmonic contrast, oriented pooling on a cell grid, facilitation and suppression of contour responses, and ridge back-projection to produce a final edge map.","audience":"Researchers and developers working on image edge detection","claims":[{"kind":"specific","claim":"Reports an ODS F-score of 0.7179 on the BRIND test set for the NMS-thinned map","excerpt":"| NMS-thinned map (`s_eval`) | 0.7179 | 0.6791 | 0.7614 | 0.7402 | 0.7651 |","status":"not_checked"},{"kind":"specific","claim":"Processes a 481×321 image in about 36 ms on an Apple M4 using MPS","excerpt":"| 481×321 | 36 ms | 124 MB | 1.1 GB |","status":"not_checked"},{"kind":"specific","claim":"Supports CUDA, Apple MPS and CPU devices, selected automatically","excerpt":"`train`, `test` and `infer` pick `cuda` when available, then `mps` on Apple silicon, then `cpu`","status":"not_checked"},{"kind":"specific","claim":"Includes a pretrained checkpoint for inference and evaluation without training","excerpt":"A pretrained checkpoint is included at `pretrained/final.pt`","status":"not_checked"},{"kind":"broad","claim":"Described as compact and fully distributed","excerpt":"A compact, fully distributed algorithm that extracts edges from RGB images","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-10"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":81,"reality":43,"gap":38,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":10,"gap_high":52,"rule":"early-2.0"},"changes":[{"date":"2026-05-22T20:33:51+00:00","text":"Repository created","source":"https://github.com/RenderBear/haci"}],"cite":"haci is a GitHub project at https://github.com/RenderBear/haci written mainly in Python, described there as \"Harmonic Contour Integration - A compact, fully distributed algorithm that extracts edges from RGB images\".","attribution":"Data from Mid or Real, https://midorreal.com/project/renderbear-haci, checked 22 November 2026. Attribution with a link is required.","still_real":null}