Conversation
The responses kernel maps get_global_id(0) to columns (dims[1]) and get_global_id(1) to rows (dims[0]), but the launch sized the grid the other way round, so on non-square images every pixel beyond the shorter dimension was skipped and its corners never reported. Extracted from #3357.
Synthetic 64x512 and 512x64 images with one bright square per 64-column band; every square's four corners must be found.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The OpenCL Harris responses kernel maps get_global_id(0) to columns and get_global_id(1) to rows, but the launch sized the grid the other way round, so on non-square images every pixel beyond the shorter dimension was skipped: a 64x512 image reports corners only in its first 64 columns, and a 512x64 image reports none at all. CUDA and CPU already do this right. The two-line fix is Stefan's from #3357, kept under his authorship; the SUSAN coordinate change in that PR is left out.
Adds
Harris.NonSquareImage, which fails against master on the OpenCL backend (4 corners found of 32) and passes with the fix. Verified on Intel Arc B580 and UHD 770; the harris suite passes on both, and the CPU backend gives the same counts.