SpatialLM · Apple GPU engineering
The model had learned.
The hardware was the hurdle.
SpatialLM can turn a scan into a room layout: walls, openings and furniture. But one operation tied it to NVIDIA hardware. I rebuilt that part so the existing model could run on a Mac.
- Problem
- One sparse-convolution operation tied SpatialLM to NVIDIA GPUs.
- Role
- I rebuilt that operation in PyTorch for Apple’s GPU and kept the authors’ trained weights.
- Result
- The model runs on a Mac laptop without retraining, checked against the reference on ten scenes.
Same understanding.
Different hardware.
The intervention
Change the part that is in the way.
SpatialLM reads a scan as sparse 3D data, and the operation that processed it depended on a library built for NVIDIA GPUs. I rebuilt that sparse-convolution operation in PyTorch for Apple’s GPU. The authors’ trained weights stayed as they were, so the model did not need retraining.
The check
Then look at what comes out.
I checked its predicted layouts against the reference for ten scenes; the table below sets the results beside the authors’ published baseline. The model now runs on a Mac laptop.
For a closer look at the engineering
Category results
F1 at 0.25 IoU: the port covers 10 scenes; the authors’ published baseline covers 107 scenes. Different scene sets mean this comparison doesn’t establish an accuracy advantage for either GPU implementation.
| Category | Chart | Pub. | Port |
|---|---|---|---|
| bed · 8 | 0.952 | 1.000 | |
| nightstand · 7 | 0.670 | 0.810 | |
| wall · 10 | 0.682 | 0.765 | |
| window · 10 | 0.514 | 0.640 | |
| door · 10 | 0.474 | 0.571 | |
| curtain · 10 | 0.370 | 0.550 | |
| wardrobe · 5 | 0.396 | 0.333 | |
| sofa small sample · 2 | 0.691 | 1.000 | |
| chair small sample · 3 | 0.323 | 0.556 | |
| chandelier small sample · 1 | 0.368 | 0.500 | |
| cabinet small sample · 3 | 0.112 | 0.222 |
Pub. is the authors’ published result; Port is the Apple GPU result. The count beside each category is the number of port scenes containing it. Categories marked “small sample” appear in three or fewer scenes.
Live products
Open what is already shipped.
Open the live demoChappie is on the App Store. The AI Bubble Index is live on this site. This page is a record of earlier work.