WAFT-Stereo

• Original code: https://github.com/princeton-vl/WAFT-Stereo at c534320860f4
• Code licence: BSD-3-Clause (permissive); files: LICENSE
• Weights licence: BSD-3-Clause
  • waft-stereo-b: CC-BY-NC-4.0
• Licence evidence: https://github.com/princeton-vl/WAFT-Stereo/blob/c534320860f4bbb2c0df896e3ccb95de49284aec/LICENSE; vendored files (net/*.py) checked against c534320: none carries an NVIDIA or FoundationStereo header, original only credits FoundationStereo in its README, so BSD-3-Clause holds
• Training data: Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa), not stated by the authors (SceneFlow, TartanAir, CREStereo, Falling Things, Sintel, Virtual KITTI 2, UnrealStereo4K, WMGStereo, CARLA, Spring, TartanGround, FSD (configs/SynLarge/*.yaml); only SceneFlow is in datasets.toml)
• Licence note: WAFT-Stereo-B is labelled CC-BY-NC-4.0 conservatively although the Hugging Face card says BSD-3-Clause: the checkpoint embeds a fine-tuned Depth Anything V2 ViT-B whose original weights are CC-BY-NC-4.0.
• Licence note: Both checkpoints were trained on data that includes NVIDIA's FSD dataset, whose terms for commercial use of trained models are unclear; the status does not depend on the training data.
• Kernel libraries: igev, cutlass_conv, cudnn_hacc, fastbb
• Variants: waft-stereo-s, waft-stereo-b
• Outputs: disparity
• Input size: any H x W >= 17, resized or padded inside the model
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): waft-stereo-s 1024x2048 (5.3 GiB peak allocated, 8.3 reserved); waft-stereo-b 1024x1024 (3.2 GiB peak allocated, 4.7 reserved)
• waft-stereo-s 994x1482, first call: portable + torch.compile 95 s (cold Inductor cache), TensorRT fp16 152 s (ONNX + engine).
• waft-stereo-s original 994x1482: torch.autocast(fp16) around the forward
• waft-stereo-b original 994x1482: torch.autocast(fp16) around the forward
• waft-stereo-s load / first call: original 1.6 s / 0.14 s (375x1242), portable 0.58 s / 0.691† s, kernels 0.3† s / 0.284† s
• waft-stereo-b load / first call: original 3.07 s / 0.444 s (375x1242), portable 1.65 s / 1.148† s, kernels 0.42† s / 0.393† 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.

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.

Limitations

• Only the two SynLarge checkpoints (S, B) are included; DAv2L-5 and the Real / KITTI / Middlebury fine-tunes are not.
• Portable WAFT-B is slightly slower than the original code and allocates slightly more memory; kernels is about 3x faster with a third of the memory.
• WAFT-Stereo-B kernels runs its ViT attention with fp16 accumulation: single attention outputs differ from fp32 by up to 34 % (relative), but end-to-end ETH3D / Middlebury-H accuracy matches the fp32 original (EPE 0.163 / 0.728).