--- library_name: "fastforks" pipeline_tag: "image-to-image" license: "other" license_name: "see-model-card" license_link: "https://github.com/princeton-vl/WAFT/blob/b152ff1cad1af8c185ee7b141997c48ff3334c87/README.md#model-zoo" tags: - "flow" - "optical-flow" - "motion-estimation" - "cuda" - "pytorch" - "fastforks" - "fastforks-card" --- # WAFT (fastforks) WAFT (Wang & Deng 2025), version a1: optical flow without a cost volume. A frozen Depth Anything V2 Small and a ResNet18 encoder give half-resolution features; each of 5 iterations warps the second image's features by the current flow and a small ViT-S (patch 8) refines the flow, which is convex-upsampled to full resolution. The authors' released weights; the network is ported from princeton-vl/WAFT. `waft-a1` is the general checkpoint the authors recommend for downstream use (TartanAir, FlyingChairs, FlyingThings3D); `-kitti` and `-sintel` are their benchmark fine-tunes. This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: . Kernels for the `kernels` backend: . Original code: at `b152ff1cad1a`. Task: flow. Tier: experimental. Outputs: `flow`. Backends: `portable`, `kernels`. Input: two RGB images (consecutive frames). Output: per-pixel motion from the first to the second (dx, dy in pixels). ## Variants Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/flow/models/waft/card.toml). | variant | weights (author link) | SHA-256 | weights licence | commercial use | |---|---|---|---|---| | `waft-a1@1` | [waft-a1-tar-c-t.pth](https://drive.usercontent.google.com/download?export=download&confirm=t&id=1CxzBQx0iSg6AyIgt6MF0ROlF_cAeZLPC) | `9f4b24f48b39` | BSD-3-Clause (assumed from code) | yes | | `waft-a1-kitti@1` | [waft-a1-tar-c-t-kitti.pth](https://drive.usercontent.google.com/download?export=download&confirm=t&id=1hzpxBe80BmPCXjo9DvSszdCRsio5vLaB) | `b600f7821a52` | BSD-3-Clause (assumed from code) | yes | | `waft-a1-sintel@1` | [waft-a1-tar-c-t-sintel.pth](https://drive.usercontent.google.com/download?export=download&confirm=t&id=1pAsbH0Orb5mFo4CLCYi4dSm6FjxrOqO3) | `e3d95a6df6ec` | BSD-3-Clause (assumed from code) | yes | ## Licence Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause. Licence files: `LICENSE`. Code licence: BSD-3-Clause; the authors do not state a separate weights licence. Training data: TartanAir, FlyingChairs (Freiburg), Freiburg SceneFlow (FlyingThings3D, Driving, Monkaa) (TartanAir pretraining, FlyingChairs, then FlyingThings3D (part of SceneFlow), as the checkpoint name tar-c-t says; the Depth Anything V2 Small inside was trained by its authors on synthetic and pseudo-labelled real images). Licence evidence: ## Input size any H x W >= 112, resized or padded inside the model Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `waft-a1` 1080x1920 (3.5 GiB peak allocated, 4.0 reserved); `waft-a1-kitti` 1080x1920 (3.5 GiB peak allocated, 4.1 reserved); `waft-a1-sintel` 1080x1920 (3.5 GiB peak allocated, 4.0 reserved) ## Speed and memory ### Flow, synthetic | model | input | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `waft-a1` | 1080x1920 | – | 1533 | 791 | 519 | 3.0x | 1.5x | 5537 / 5916 | 3553 / 4076 | 1851 / 2264 | | `waft-a1-kitti` | 1080x1920 | – | 1533 | 791 | – | – | – | 5537 / 5936 | 3553 / 4196 | – | | `waft-a1-sintel` | 1080x1920 | – | 1533 | 791 | – | – | – | 5537 / 5916 | 3553 / 4076 | – | ### Startup and first call | model | load (s): original | portable | kernels | first call (s): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | | `waft-a1` | 5.87 | 0.51 | 0.57 (375x1242) | 3.41 | 0.79 | 0.21 (375x1242) | | `waft-a1-kitti` | 4.06 | 0.54 | – | 2.87 | 0.79 | – | | `waft-a1-sintel` | 2.93 | 0.51 | – | 2.87 | 0.79 | – | ### torch.compile and TensorRT | model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `waft-a1` | 1080x1920 | 791 ms | 610 ms | deferred (build >5 min) | 519 ms | 84.7 s | – | 3553 / 4076 | 3479 / 3638 | 1851 / 2264 | – | | `waft-a1-kitti` | 1080x1920 | 791 ms | 610 ms | deferred (build >5 min) | – | 84.1 s | – | 3553 / 4196 | 3479 / 3758 | – | – | | `waft-a1-sintel` | 1080x1920 | 791 ms | 610 ms | deferred (build >5 min) | – | 84.7 s | – | 3553 / 4076 | 3479 / 3578 | – | – | Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB). Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's. ## Accuracy ### On public datasets Frames _10 -> _11 at full size against the flow_occ ground truth; EPE = mean of the per-pair mean end-point error, Fl-all = share of all valid pixels with an error > 3 px and > 5 % of the GT magnitude. Original = the original code named under Details, same checkpoint and protocol. | variant | dataset | original fp32 | original fp16 | portable | note | |---|---|---|---|---|---| | `waft-a1` | KITTI 2015 train, EPE / Fl-all % | 2.395 / 8.52 | 2.375 / 8.52 | 2.315 / 8.51 | | Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks ec1d48ea, 2026-11-14. ### Parity with the original code Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.005 and p99 <= 0.02 (absolute error of the output `flow`). ## Usage ```python from fastforks import flow model = flow.load("waft-a1") # mode="auto": the preferred backend from recorded measurements result = model("frame1.png", "frame2.png") result.flow # [2, H, W] float32 tensor: dx, dy in input pixels result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16') ``` Install with `pip install fastforks` (see ). Other variants: `waft-a1`, `waft-a1-kitti`, `waft-a1-sintel`. ## Kernels backend `flow.load("waft-a1", mode="kernels")` runs our CUDA kernels (`igev`, `cutlass_conv`, `cudnn_hacc`, `fastbb`, `dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.