ComfyUI Node
Add HiRes Views to Dataset
A ComfyUI node in SplatKit with 9 inputs and 4 outputs.
Add HiRes Views to Dataset
- frames
- splat_mask
- dataset_dir
- report
- num_registered
- num_points
◄cameras_json—►
◄dataset_dir►
◄retriangulatetrue►
◄adjust_existing_camerasfalse►
◄match_stride1►
◄max_num_features8192►
◄abs_pose_min_num_inliers30►
CategorySplatKit
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| frames | IMAGE | The HiRes node's 'frames' output. | |
| cameras_json | STRING | The HiRes node's 'cameras_json' output -- carries the exact intrinsics (K) so the views register with true, not estimated, focal length. | |
| dataset_dir | STRING | The EXISTING SphereSfM dataset to add to -- wire the Dataset Project node's dataset_dir here (the same value the base SphereSfM node used as output_name), or type the dataset folder name/path. It is the folder holding images/, sparse/ and _spheresfm_work/, and must have been built with mode=colmap_now -- the add needs the original spherical reconstruction to register against. | |
| retriangulateopt | BOOLEAN | true | Re-triangulate the sparse cloud including the hires views, so they contribute real 3D points to the splat's init cloud (measured +7% points on the cafe dataset). Off = poses only. |
| adjust_existing_camerasopt | BOOLEAN | false | Let bundle adjustment MOVE the existing panorama cameras to fit the new views. Off (default) pins them, so the add is purely additive and cannot break a dataset that already trains. Turn on only if the base reconstruction is shaky. |
| match_strideopt | INT | 11–10 | Match each hires view against every Nth existing frame. 1 = all (best). Raise it on very long base trajectories to cut the pair count -- neighbouring pano frames are near-duplicates, so 2-3 still ties the views in. |
| max_num_featuresopt | INT | 81921024–32768 | SIFT features per image. Raise if views fail to register. |
| abs_pose_min_num_inliersopt | INT | 3010–300 | Inliers needed to accept a view's pose. Lower = more views register, at the risk of a bad pose sneaking in. |
| splat_maskopt | IMAGE | The HiRes node's 'splat_mask' output (white = real pano detail, black = synthesized/stretched). When wired, per-view masks land in <dataset>/masks/ so splat trainers can exclude the fake pixels from the loss: nerfstudio trains with '--masks-path masks', Brush picks the folder up automatically. The cube faces get all-white masks so every image has one (nerfstudio requires all-or-none). |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| dataset_dir | STRING | — |
| report | STRING | — |
| num_registered | INT | — |
| num_points | INT | — |