Client-side stereo detection transfer via ONNX (first pass)#1709
Open
mattdawkins wants to merge 10 commits into
Open
Client-side stereo detection transfer via ONNX (first pass)#1709mattdawkins wants to merge 10 commits into
mattdawkins wants to merge 10 commits into
Conversation
Brings in the SAM2/SAM3-based interactive segmentation feature, the SAM3 text-query workflow, and the desktop interactive stereo mode. Web-girder paths are intentionally untouched for now — web support will come in a follow-up. - New segmentation point-click recipe + EditorMenu wiring; SAM2/SAM3 models loaded via VIAME install configs. - Desktop backend: viame_segmentation_service-backed IPC handlers and matching frontend API for segmentationInitialize/Predict/SetImage/ ClearImage/Shutdown/IsReady, textQuery/refineDetections/ runTextQueryPipeline, and stereoEnable/Disable/SetFrame/GetStatus/ TransferLine/TransferPoints/SetCalibration/IsEnabled, plus disparity ready/error event hooks. - EditAnnotationLayer: track shift-key state and right-click for Point mode, propagate background flag for negative SAM points. - Sidebar / ViewerLoader / Viewer: stereo annotation mode UI, error dialog when seg or text-query model fails to load, dot-only-on-source -frame fix. - useModeManager / EditAnnotationLayer / recipes: keep existing geometry type when current editing mode already matches; right-click in Point creation finalises and deselects.
A track-frame's polygon now expands to a list of polygons each with their own keys, and each polygon supports holes. - Server CSV (de)serializer: emit polygon-key column per polygon, support holes in the geoJSON FeatureCollection; auto_key path to append a new polygon to an existing track frame. - Client recipes / useModeManager: handleAddHole / handleAddPolygon / handleCancelCreation; PolygonLayer emits polygon-clicked. - Hole drawing reuses the polygon edit pipeline (left-click places a hole vertex without exiting creation mode). - Test fixtures cover multi-polygon and polygons-with-holes round-trip.
(cherry picked from commit c2f3cd0)
(cherry picked from commit 3db1995)
(cherry picked from commit b7d4fa3)
(cherry picked from commit f5d015a)
…tton) Strip the SAM3 text-query button, dialog, API, and IPC handlers from the interactive editor, keeping segmentation and stereo intact. The full text-query feature lives on the follow-up branch dev/text-query-annot-button.
Strip the no-transcode NativeVideoAnnotator path that should not be on the segmentation/stereo branch: removes the residual Viewer.vue async-component, nativeVideoPath plumbing, and template branch, plus the stale settings field.
The rebase onto main dropped the opening <template> tag, so vite parsed the root <div> as a custom block and the electron build failed. Restore it.
mattdawkins
force-pushed
the
dev/stereo-onnx-transfer
branch
from
eb3573d to
42ca8d8
Compare
Runs VIAME's epipolar template-matching model (stereo method 1) in the browser with onnxruntime-web to warp a detection (box / head-tail keypoints) from one camera to the other, with no backend. Includes calibration (.npz/.json) and grayscale helpers, a platform-agnostic transfer composable, and web ViewerLoader wiring. Core is validated against the VIAME reference in unit tests.
mattdawkins
force-pushed
the
dev/stereo-onnx-transfer
branch
from
42ca8d8 to
a55690f
Compare
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
1 participant
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.
First pass at warping a detection from one camera to the other entirely
client-side (web + Electron renderer), with no backend, by running VIAME's
epipolar template-matching stereo model (stereo measurement "method 1")
exported to ONNX and executed with onnxruntime-web.
This is the client counterpart to the desktop backend stereo service: the
desktop ViewerLoader warps via native IPC (
stereoTransferLine/stereoTransferPoints); this does the equivalent correspondence search in thebrowser so it also works on the web.
What's here (
client/dive-common/use/stereo/)StereoOnnxMatcher— loads thematchONNX model and warps source points totarget points (epipolar candidate generation + NCC along the curve).
calibration.ts/npz.ts— parse.npz/.jsoncalibration in-browser(mirrors
read_stereo_rig), plusinvertRigto swap source/target camera.image.ts— RGBA to BT.601 grayscale (matches OpenCV BGR2GRAY used by the NCC).frameSource.ts— read full-res frame pixels from a GeoJS viewer.useStereoOnnxTransfer— onstereo-annotation-complete, warp a box (corners)or head/tail line (keypoints) to the other camera and write the feature.
platform/web-girder/useStereoOnnxWeb.ts, bound to the Viewer'sstereo-annotation-completeevent in the webViewerLoader.vue.onnxruntime-webis added as a dependency. The exported model is served as astatic asset (default
/models/stereo_match.onnx).Testing
__tests__/stereoOnnx.spec.ts, runs undernpm test):calibration parsing, grayscale, and point warping validated against the VIAME
C++/Python reference (matches to ~0.25 px) via onnxruntime-web in Node.
type-checked and lint-clean but has not been live-tested in a running web
viewer with a real stereo dataset.
Notes
setting.