PSMNet · fastforks

A classic stereo network by Jia-Ren Chang with a spatial-pyramid backbone and stacked 3D hourglasses. Commercially usable.

Commercial use: yes.

variant	input	backend	time (ms)	peak memory (MiB, allocated / reserved)
`psmnet-sceneflow`	Middlebury 2014 half (994x1482)	original (fp32) original portable kernels portable + torch.compile TensorRT fp16	760 608 340 232 440 669	7544 / 7640 6015 / 6090 2078 / 2442 1786 / 2122 1760 / 2082 1528 (engine)

Details

Original code: https://github.com/JiaRenChang/PSMNet at 87ac9093afbf
Code licence: MIT (permissive); files: LICENSE
Weights licence: MIT (assumed from code)
Licence evidence: https://github.com/JiaRenChang/PSMNet/blob/87ac9093afbf6545c093bd9d26c5ffd66e49a7b8/README.md#L96-L98
Training data: Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa)
Kernel libraries: igev, cutlass_conv, cudnn_hacc
Variants: psmnet-sceneflow
Outputs: disparity
Input size: any H x W >= 241, padded to a multiple of 16
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): psmnet-sceneflow 1988x2880 (7.6 GiB peak allocated, 10.6 reserved)
psmnet-sceneflow 994x1482, first call: portable + torch.compile 60 s (cold Inductor cache), TensorRT fp16 89 s (ONNX + engine).
psmnet-sceneflow original 994x1482: torch.autocast(fp16) around the forward
psmnet-sceneflow load / first call: original 0.2 s / 0.525 s (375x1242), portable 0.1 s / 0.352† s, kernels 0.08† s / 0.232† s
† measured in the speed sweep after the portable load (or an earlier size) in the same process: file cache and kernels are warm, so the time is lower than a fresh start.
Protocol, median of 5 after 3 warm-up, uint8 CUDA input (synthetic for bench_inputs sizes), card defaults; gc before each load; peak = max over the first call and the timed calls

Original = the original code named under Details, same checkpoint and protocol.

variant	dataset	original fp32	original fp16	portable	kernels	note
`psmnet-sceneflow`	ETH3D two-view train, bad > 1 px % / EPE	15.14 / 2.152	15.13 / 2.152	15.11 / 2.154	15.13 / 2.148
`psmnet-sceneflow`	Middlebury 2014 trainingH, bad > 2 px % / EPE	36.06 / 11.482	36.06 / 11.484	36.06 / 11.484	36.07 / 11.482

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 468fba10, 2026-11-05.

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.05 px and p99 <= 0.5 px.

variant	kernels error vs original, mean / p99	GPU, torch	kernels used
`psmnet-sceneflow`	0.00412 / 0.01422	RTX 5060 Ti, torch 2.14.1+cu130	`cudnn_hacc@cudnn92400`, `cutlass_conv@988138e042cb:sm_120`, `igev@f075827d68c6:sm_120`