any2full / README.md
Flor's picture
card: update from fastforks 1cbf1671
e014483 verified
|
Raw History Blame Contribute Delete
7.43 kB
metadata
library_name: fastforks
pipeline_tag: depth-estimation
license: apache-2.0
tags:
  - depth
  - mono-depth
  - monocular-depth
  - cuda
  - pytorch
  - fastforks
  - fastforks-card

Any2Full (fastforks)

Any2Full (2026): one-stage depth completion that prompts Depth Anything V2 with a sparse depth map of any pattern and density; the depth tokens modulate the ViT features entering the DPT head, the disparity is fitted to the prompt.

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: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/zhiyuandaily/Any2Full at 780edf6.

Author weight repos: https://huggingface.co/zhiyuandaily/Any2Full.

Task: depth. Tier: experimental. Outputs: depth. Backends: portable, kernels.

Input: one RGB image. Output: a depth or inverse-depth map. kind (a card field, result.kind) says what the numbers mean: metric = metres; scale_invariant, affine_invariant, affine_invariant_log (log depth) and affine_invariant_inverse are relative (unknown scale or shift, not metres). Metric models that use the focal length take model(image, intrinsics=K) (K [3, 3], pixels of the input): metric3d-vit-large and da3metric-large need it for correct metres (da3metric-large: metres = output x focal / 300; without intrinsics= a 300 px focal length is assumed, wrong for a real camera). unidepth-v2-vitl14, unik3d-vitl, depth-pro and MoGe estimate the camera themselves (given intrinsics= replace fx); zoedepth-nk and the relative models (da3mono-large too) take none. Normals-only models (kind none) return result.normals [B, H, W, 3] (unit vectors, camera frame: x right, y down, z forward).

Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.

variant weights (author link) SHA-256 weights licence commercial use
any2full-b@1 Any2Full_vitb.pth.tar 5afd2519e061 Apache-2.0 yes
any2full-l@1 Any2Full_vitl.pth.tar ea2809c9c490 Apache-2.0 yes
any2full-s@1 Any2Full_vits.pth.tar c797e3b93a1b Apache-2.0 yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Licence files: LICENSE.

Training data: Training data and code not released yet (arXiv 2603.05711); the ViT and head start from Depth Anything V2.

Licence evidence: https://github.com/zhiyuandaily/Any2Full/blob/main/LICENSE and the Hugging Face model card zhiyuandaily/Any2Full (license: apache-2.0)

Input size

any H x W >= 1, resized or padded inside the model (ViT patch 14) Tested up to (portable, fp16, RTX 5060 Ti 16 GB): any2full-b 3000x4000 (0.7 GiB peak allocated, 0.9 reserved); any2full-l 3000x4000 (1.2 GiB peak allocated, 1.3 reserved); any2full-s 3000x4000 (0.5 GiB peak allocated, 0.6 reserved)

Speed and memory

Depth, 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
any2full-b 994x1482 – – 26.8 – – – – 538 / 596 –
any2full-l 994x1482 – – 67.7 – – – – 1178 / 1250 –
any2full-s 994x1482 – – 12.4 – – – – 274 / 312 –

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
any2full-b – 6.38 – – 3.34 –
any2full-l – 1.45 – – 0.30 –
any2full-s – 0.31 – – 0.36 –

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)
any2full-b 994x1482 26.8 ms 24.2 ms deferred (build >5 min) – 97.0 s – 538 / 596 442 / 496 – –
any2full-l 994x1482 67.7 ms 63.8 ms deferred (build >5 min) – 33.9 s – 1178 / 1250 987 / 1092 – –
any2full-s 994x1482 12.4 ms deferred (build >5 min) deferred (build >5 min) – – – 274 / 312 – – –

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: benchmarks (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

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.005 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 1.5 % and p99 <= 5 % of the reference's median |value| (absolute error of the output depth).

Limitations

  • The depth map is required: call the model with prompt_depth= a metric map in metres (any size, sparse points or holes as 0 / NaN / inf). The output is fitted to it by scale and shift in disparity, so it needs at least two distinct valid values.
  • Export has a fixed input size.

Usage

from fastforks import depth

model = depth.load("any2full-b")  # mode="auto": the preferred backend from recorded measurements
result = model("room.jpg")
result.depth  # [H, W] float32 tensor; result.kind says what the maps mean
# models that take a camera: model("room.jpg", intrinsics=K), K [3, 3] in pixels
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')

Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: any2full-b, any2full-l, any2full-s.

Kernels backend

depth.load("any2full-b", mode="kernels") runs our CUDA kernels (fastbb, dpt_fused). It needs a prebuilt kernel for your GPU architecture (downloaded from https://huggingface.co/fastforks/kernels 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.