RAFT-Stereo · fastforks

A recurrent stereo network from the Princeton Vision & Learning Lab, with checkpoints for several datasets. Commercially usable.

Commercial use: yes.

variant	input	backend	time (ms)	peak memory (MiB, allocated / reserved)
`raft-stereo-middlebury`	Middlebury 2014 half (994x1482)	original (fp32) original portable kernels	1775 1037 746 273	4825 / 4928 2516 / 2628 1388 / 1492 765 / 802

Details

Original code: https://github.com/princeton-vl/RAFT-Stereo at 6e93ed2169bd
Code licence: MIT (permissive); files: LICENSE
Weights licence: MIT (assumed from code)
Licence evidence: https://github.com/princeton-vl/RAFT-Stereo/blob/6e93ed2169bd858dbb43033988563f3b0bb49506/README.md#L79
Training data: Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa)
- raft-stereo-middlebury: Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa), Middlebury stereo (2014) (SceneFlow, then fine-tuned on the 23 Middlebury 2014 training scenes)
- raft-stereo-eth3d: ETH3D submission model
Options: iters = 32 (>= 1)
Kernel libraries: raft, cutlass_conv, cudnn_hacc
Variants: raft-stereo-middlebury, raft-stereo-sceneflow, raft-stereo-eth3d
Outputs: disparity
Input size: any H x W >= 32, padded to a multiple of 32
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): raft-stereo-middlebury 3000x4000 (10.2 GiB peak allocated, 12.5 reserved); raft-stereo-sceneflow 3000x4000 (10.2 GiB peak allocated, 12.5 reserved); raft-stereo-eth3d 3000x4000 (10.2 GiB peak allocated, 12.5 reserved)
raft-stereo-sceneflow, raft-stereo-eth3d: same network and settings as raft-stereo-middlebury, measured once (rows not repeated).
raft-stereo-middlebury original (fp32) 994x1482, original 994x1482: timed with raft-stereo-eth3d (same network, other weights); corr_implementation=reg_cuda
raft-stereo-middlebury portable 994x1482, kernels 994x1482: measured on raft-stereo-eth3d (same architecture, other checkpoint)
raft-stereo-middlebury load / first call: original 0.27 s / 1.452 s (375x1242), portable 0.25 s / 0.746† s, kernels 0.05† s / 0.273† s
raft-stereo-sceneflow load / first call: original 0.27 s / 1.452 s (375x1242), portable 0.25 s / 0.746† s, kernels 0.05† s / 0.273† s
raft-stereo-eth3d load / first call: original 0.27 s / 1.452 s (375x1242), portable 0.25 s / 0.746† s, kernels 0.05† s / 0.273† 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

Measured

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

variant	dataset	original fp32	original fp16	portable	kernels	note
`raft-stereo-middlebury`	ETH3D two-view train, bad > 1 px % / EPE	2.77 / 0.287	2.77 / 0.289	2.77 / 0.289	2.79 / 0.289
`raft-stereo-middlebury`	Middlebury 2014 trainingH, bad > 2 px % / EPE	7.20 / 1.069	7.19 / 1.069	7.20 / 1.069	7.21 / 1.071	trained on this dataset's public images; not a zero-shot result
`raft-stereo-sceneflow`	ETH3D two-view train, bad > 1 px % / EPE	2.61 / 0.266	2.61 / 0.267	2.60 / 0.267	2.60 / 0.267
`raft-stereo-sceneflow`	Middlebury 2014 trainingH, bad > 2 px % / EPE	11.22 / 1.436	11.21 / 1.439	11.23 / 1.438	11.23 / 1.452
`raft-stereo-eth3d`	ETH3D two-view train, bad > 1 px % / EPE	2.61 / 0.274	2.60 / 0.274	2.60 / 0.274	2.61 / 0.274	possibly in the training data
`raft-stereo-eth3d`	Middlebury 2014 trainingH, bad > 2 px % / EPE	11.95 / 1.635	11.99 / 1.634	12.00 / 1.635	11.98 / 1.635	possibly in the training data

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

Parity

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 px and p99 <= 0.25 px.

variant	kernels error vs original, mean / p99	GPU, torch	kernels used
`raft-stereo-middlebury`	0.00836 / 0.07899	RTX 5060 Ti, torch 2.14.1+cu130	`cudnn_hacc@cudnn92400`, `cutlass_conv@988138e042cb:sm_120`, `raft@9524a68234cc:sm_120`
`raft-stereo-sceneflow`	0.0019 / 0.01941	RTX 5060 Ti, torch 2.14.1+cu130	`cudnn_hacc@cudnn92400`, `cutlass_conv@988138e042cb:sm_120`, `raft@9524a68234cc:sm_120`
`raft-stereo-eth3d`	0.00166 / 0.01285	RTX 5060 Ti, torch 2.14.1+cu130	`cudnn_hacc@cudnn92400`, `cutlass_conv@988138e042cb:sm_120`, `raft@9524a68234cc:sm_120`

Limitations

raftstereo-realtime.pth and iraftstereo_rvc.pth from the original zip (another architecture / instance-norm context) are not included and not supported by the kernels engine.