Depth Anything V2 (fastforks)

Depth Anything V2 (Yang et al. 2024): relative monocular depth from a DINOv2 ViT encoder and a DPT head, trained on synthetic labels and 62M pseudo-labelled real images; with the authors' metric fine-tunes (Hypersim indoor, Virtual KITTI 2 outdoor) and the Distill-Any-Depth checkpoints (He et al. 2025) of the same network.

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/DepthAnything/Depth-Anything-V2 at a561b84.

Author weight repos: https://huggingface.co/depth-anything/Depth-Anything-V2-Base, https://huggingface.co/depth-anything/Depth-Anything-V2-Large, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Base, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Large, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Small, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Base, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Large, https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Small, https://huggingface.co/depth-anything/Depth-Anything-V2-Small, https://huggingface.co/xingyang1/Distill-Any-Depth.

Task: depth. Tier: stable. Outputs: inverse_depth, 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
depth-anything-v2-b@1 depth_anything_v2_vitb.pth 0d2b7002e62d CC-BY-NC-4.0 no
depth-anything-v2-l@1 depth_anything_v2_vitl.pth a7ea19fa0ed9 CC-BY-NC-4.0 no
depth-anything-v2-metric-hypersim-b@1 depth_anything_v2_metric_hypersim_vitb.pth 9dc9e274c5ef Apache-2.0 yes
depth-anything-v2-metric-hypersim-l@1 depth_anything_v2_metric_hypersim_vitl.pth 6f82ff2bc543 Apache-2.0 yes
depth-anything-v2-metric-hypersim-s@1 depth_anything_v2_metric_hypersim_vits.pth b782898d8a3e Apache-2.0 yes
depth-anything-v2-metric-vkitti-b@1 depth_anything_v2_metric_vkitti_vitb.pth 4dad67a7cc10 Apache-2.0 yes
depth-anything-v2-metric-vkitti-l@1 depth_anything_v2_metric_vkitti_vitl.pth 239b1054a369 Apache-2.0 yes
depth-anything-v2-metric-vkitti-s@1 depth_anything_v2_metric_vkitti_vits.pth 9203e538d352 Apache-2.0 yes
depth-anything-v2-s@1 depth_anything_v2_vits.pth 715fade13be8 Apache-2.0 yes
distill-any-depth-b@1 Distill-Any-Depth/base/model.safetensors ee99258af6c4 Apache-2.0 yes
distill-any-depth-l@1 Distill-Any-Depth/large/model.safetensors c7d46f6f0048 Apache-2.0 yes
distill-any-depth-s@1 Distill-Any-Depth/small/model.safetensors 56a173c0e1b5 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: Teacher (ViT-G) on 595K synthetic images (BlendedMVS, Hypersim, IRS, TartanAir, VKITTI 2); students on 62M pseudo-labelled real images (SA-1B, Open Images, BDD100K, Google Landmarks, ImageNet-21K, LSUN, Objects365, Places365) per the paper.

  • Licence note: Only the Small weights are Apache-2.0; the Base and Large weights are CC-BY-NC-4.0. The training data of even the Small model has unclear commercial terms (a note only).
  • Licence note: The six metric checkpoints are Apache-2.0 on their Hugging Face cards, but the Base / Large ones are fine-tuned from the CC-BY-NC-4.0 relative Base / Large weights, and Virtual KITTI 2 (the outdoor fine-tune) is CC BY-NC-SA 3.0, Hypersim CC BY-SA 3.0.
  • Licence note: Distill-Any-Depth: Apache-2.0 on the Hugging Face card (the authors' transformers ports say MIT, the code is MIT). The paper initialises the Large model from the CC-BY-NC-4.0 Depth Anything V2 Large weights; its teachers include Depth Anything V2 and it trains on unlabeled SA-1B images (research licence).

Licence evidence: https://github.com/DepthAnything/Depth-Anything-V2/blob/main/README.md (LICENSE section) and the Hugging Face model cards

Input size

  • depth-anything-v2-b, depth-anything-v2-l, depth-anything-v2-s: any H x W >= 8, resized or padded inside the model (ViT patch 14)
  • depth-anything-v2-metric-hypersim-b, depth-anything-v2-metric-hypersim-l, depth-anything-v2-metric-hypersim-s, depth-anything-v2-metric-vkitti-b, depth-anything-v2-metric-vkitti-l, depth-anything-v2-metric-vkitti-s, distill-any-depth-b, distill-any-depth-l, distill-any-depth-s: any H x W >= 1, resized or padded inside the model (ViT patch 14) Tested up to (portable, fp16, RTX 5060 Ti 16 GB): depth-anything-v2-b 3000x4000 (0.8 GiB peak allocated, 0.9 reserved); depth-anything-v2-l 3000x4000 (1.8 GiB peak allocated, 2.2 reserved); depth-anything-v2-metric-hypersim-b 3000x4000 (0.6 GiB peak allocated, 0.7 reserved); depth-anything-v2-metric-hypersim-l 3000x4000 (1.1 GiB peak allocated, 1.2 reserved); depth-anything-v2-metric-hypersim-s 3000x4000 (0.5 GiB peak allocated, 0.5 reserved); depth-anything-v2-metric-vkitti-b 3000x4000 (0.6 GiB peak allocated, 0.7 reserved); depth-anything-v2-metric-vkitti-l 3000x4000 (1.1 GiB peak allocated, 1.2 reserved); depth-anything-v2-metric-vkitti-s 3000x4000 (0.5 GiB peak allocated, 0.5 reserved); depth-anything-v2-s 3000x4000 (0.5 GiB peak allocated, 0.5 reserved); distill-any-depth-b 3000x4000 (0.6 GiB peak allocated, 0.7 reserved); distill-any-depth-l 3000x4000 (1.1 GiB peak allocated, 1.2 reserved); distill-any-depth-s 3000x4000 (0.5 GiB peak allocated, 0.5 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
depth-anything-v2-b 518x770 88.8 53.8 18.8 10.6 5.1x 1.8x 928 / 1026 433 / 516 370 / 436
depth-anything-v2-l 518x770 240 136 55.0 31.6 4.3x 1.7x 2560 / 2654 1009 / 1352 904 / 1034
depth-anything-v2-metric-hypersim-b 994x1482 โ€“ โ€“ 18.6 10.8 โ€“ 1.7x โ€“ 445 / 514 349 / 396
depth-anything-v2-metric-hypersim-l 994x1482 โ€“ โ€“ 54.5 31.7 โ€“ 1.7x โ€“ 1022 / 1092 917 / 1034
depth-anything-v2-metric-hypersim-s 994x1482 โ€“ โ€“ 7.66 4.67 โ€“ 1.6x โ€“ 244 / 288 152 / 208
depth-anything-v2-metric-vkitti-l 994x1482 โ€“ โ€“ 54.5 31.9 โ€“ 1.7x โ€“ 1022 / 1092 917 / 1034
depth-anything-v2-s 518x770 45.5 38.1 7.73 4.45 8.6x 1.7x 373 / 418 232 / 326 173 / 248
distill-any-depth-l 994x1482 โ€“ โ€“ 54.4 31.8 โ€“ 1.7x โ€“ 1022 / 1092 917 / 1034
distill-any-depth-s 994x1482 โ€“ โ€“ 7.65 4.63 โ€“ 1.7x โ€“ 244 / 288 152 / 208

Depth, Middlebury 2014 half, 994x1482

model time (ms): original fp32 original portable kernels kernels speed-up: vs original vs portable peak memory (MiB, allocated / reserved): original portable kernels
depth-anything-v2-b 93.6 63.2 18.8 10.5 6.0x 1.8x 928 / 1026 450 / 516 387 / 436
depth-anything-v2-l 245 140 55.1 31.1 4.5x 1.8x 2560 / 2654 1026 / 1352 921 / 1034
depth-anything-v2-metric-hypersim-b 91.4 60.7 โ€“ โ€“ โ€“ โ€“ 928 / 1026 โ€“ โ€“
depth-anything-v2-metric-hypersim-l 246 141 โ€“ โ€“ โ€“ โ€“ 2560 / 2654 โ€“ โ€“
depth-anything-v2-metric-hypersim-s 53.0 43.6 โ€“ โ€“ โ€“ โ€“ 373 / 418 โ€“ โ€“
depth-anything-v2-metric-vkitti-b 90.8 60.6 โ€“ โ€“ โ€“ โ€“ 928 / 1026 โ€“ โ€“
depth-anything-v2-metric-vkitti-l 245 141 โ€“ โ€“ โ€“ โ€“ 2560 / 2654 โ€“ โ€“
depth-anything-v2-metric-vkitti-s 46.1 36.0 โ€“ โ€“ โ€“ โ€“ 373 / 418 โ€“ โ€“
depth-anything-v2-s 53.6 41.0 7.82 4.51 9.1x 1.7x 373 / 418 249 / 326 190 / 248
distill-any-depth-b 90.5 59.8 โ€“ โ€“ โ€“ โ€“ 928 / 1026 โ€“ โ€“
distill-any-depth-l 244 139 โ€“ โ€“ โ€“ โ€“ 2560 / 2654 โ€“ โ€“
distill-any-depth-s 45.3 35.2 โ€“ โ€“ โ€“ โ€“ 373 / 418 โ€“ โ€“

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
depth-anything-v2-b 3.94 0.85 0.20โ€  0.08 0.02 0.01
depth-anything-v2-l 5.66 2.39 0.91โ€  0.15 0.08 0.06
depth-anything-v2-metric-hypersim-b 2.13 0.33 (518x770) 1.13 (518x770) 0.07 0.27 (518x770) 0.05 (518x770)
depth-anything-v2-metric-hypersim-l 4.87 0.84 (518x770) 1.73 (518x770) 0.15 0.15 (518x770) 0.07 (518x770)
depth-anything-v2-metric-hypersim-s 1.54 0.19 (518x770) 0.95 (518x770) 0.17 0.23 (518x770) 0.06 (518x770)
depth-anything-v2-metric-vkitti-b 2.06 0.30 (518x770) 1.13 (518x770) 0.06 0.28 (518x770) 0.05 (518x770)
depth-anything-v2-metric-vkitti-l 4.87 0.84 (518x770) 1.65 (518x770) 0.14 0.15 (518x770) 0.05 (518x770)
depth-anything-v2-metric-vkitti-s 1.46 0.13 (518x770) 0.96 (518x770) 0.04 0.16 (518x770) 0.05 (518x770)
depth-anything-v2-s 0.71 0.11 0.08โ€  0.38 0.03 0.01
distill-any-depth-b 0.84 0.29 (518x770) 1.13 (518x770) 0.06 0.27 (518x770) 0.04 (518x770)
distill-any-depth-l 3.03 0.82 (518x770) 1.68 (518x770) 0.14 0.14 (518x770) 0.06 (518x770)
distill-any-depth-s 0.25 0.13 (518x770) 0.96 (518x770) 0.04 0.16 (518x770) 0.04 (518x770)

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)
depth-anything-v2-b 994x1482 18.8 ms 17.0 ms 10.9 ms 10.5 ms 14.2 s 32.7 s 450 / 516 340 / 394 387 / 436 539 / 596
depth-anything-v2-l 994x1482 55.1 ms 51.7 ms 32.4 ms 31.1 ms 20.6 s 43.5 s 1026 / 1352 850 / 952 921 / 1034 1579 / 1634
depth-anything-v2-metric-hypersim-b 994x1482 18.6 ms 17.0 ms 10.8 ms 10.8 ms 16.0 s 32.0 s 445 / 514 340 / 394 349 / 396 539 / 614
depth-anything-v2-metric-hypersim-l 994x1482 54.5 ms 51.3 ms 32.3 ms 31.7 ms 20.2 s 43.5 s 1022 / 1092 850 / 910 917 / 1034 1579 / 1634
depth-anything-v2-metric-hypersim-s 994x1482 7.66 ms 6.67 ms 4.47 ms 4.67 ms 15.8 s 29.8 s 244 / 288 201 / 224 152 / 208 305 / 348
depth-anything-v2-metric-vkitti-b 994x1482 18.6 ms 17.0 ms 10.9 ms 10.8 ms 15.9 s 32.0 s 445 / 514 340 / 394 349 / 396 539 / 614
depth-anything-v2-metric-vkitti-l 994x1482 54.5 ms 51.3 ms 32.4 ms 31.9 ms 20.1 s 43.4 s 1022 / 1092 850 / 910 917 / 1034 1579 / 1634
depth-anything-v2-metric-vkitti-s 994x1482 7.66 ms 6.68 ms 4.47 ms 4.67 ms 15.8 s 29.9 s 244 / 288 201 / 224 152 / 208 305 / 348
depth-anything-v2-s 994x1482 7.82 ms 6.65 ms 4.46 ms 4.51 ms 15.7 s 29.9 s 249 / 326 201 / 224 190 / 248 273 / 308
distill-any-depth-b 994x1482 18.6 ms 17.0 ms 10.8 ms 10.8 ms 16.2 s 33.0 s 445 / 514 340 / 394 349 / 396 539 / 614
distill-any-depth-l 994x1482 54.4 ms 51.6 ms 32.4 ms 31.8 ms 20.1 s 42.5 s 1022 / 1092 850 / 910 917 / 1034 1579 / 1634
distill-any-depth-s 994x1482 7.65 ms 6.67 ms 4.46 ms 4.63 ms 15.9 s 29.9 s 244 / 288 201 / 224 152 / 208 305 / 348

Fixed-size speed and peak memory, all models

model mode 480x640 720x1280 1080x1920 12 MP 3000x4000
depth-anything-v2-b portable 18.8 ms / 643 / 776 26.2 ms / 733 / 876 26.3 ms / 745 / 908 20.0 ms / 787 / 924
depth-anything-v2-b kernels 9.5 ms / 325 / 408 13.6 ms / 376 / 466 13.7 ms / 390 / 486 10.7 ms / 606 / 622
depth-anything-v2-l portable 55.9 ms / 1752 / 1946 78.6 ms / 1915 / 2170 78.8 ms / 1928 / 2180 57.1 ms / 1885 / 2216
depth-anything-v2-l kernels 28.3 ms / 875 / 1000 38.7 ms / 965 / 1104 38.8 ms / 977 / 1112 29.3 ms / 1058 / 1174
depth-anything-v2-s portable 8.1 ms / 262 / 326 10.9 ms / 314 / 376 11.0 ms / 329 / 422 9.5 ms / 509 / 536
depth-anything-v2-s kernels 4.0 ms / 129 / 166 5.7 ms / 164 / 218 5.8 ms / 177 / 214 5.1 ms / 462 / 480

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

  • depth-anything-v2-metric-vkitti-b, distill-any-depth-b: same network and settings as depth-anything-v2-metric-hypersim-b, measured once (rows not repeated).
  • depth-anything-v2-metric-vkitti-s: same network and settings as depth-anything-v2-metric-hypersim-s, measured once (rows not repeated).

Resizes to its working resolution: time depends on the aspect ratio, not the input pixels.

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

On public datasets

AbsRel / delta1 after a least-squares scale + shift fit (in disparity space for inverse-depth models), mean over images. Original = the original code named under Details, same checkpoint and protocol.

variant dataset original fp32 original fp16 portable kernels note
depth-anything-v2-s NYUv2 test, AbsRel / delta1 0.0509 / 0.9780 0.0509 / 0.9780 0.0509 / 0.9780 0.0509 / 0.9780
depth-anything-v2-s iBims-1, AbsRel / delta1 0.0448 / 0.9744 0.0448 / 0.9744 0.0448 / 0.9744 0.0448 / 0.9744
depth-anything-v2-s ETH3D two-view train left, AbsRel / delta1 0.0803 / 0.9256 0.0803 / 0.9256 0.0803 / 0.9256 0.0803 / 0.9256 possibly in the training data
depth-anything-v2-s Middlebury 2014 trainingH left, AbsRel / delta1 0.0346 / 0.9947 0.0346 / 0.9947 0.0346 / 0.9947 0.0346 / 0.9947 possibly in the training data
depth-anything-v2-b NYUv2 test, AbsRel / delta1 0.0462 / 0.9806 0.0462 / 0.9806 0.0462 / 0.9806 0.0462 / 0.9806
depth-anything-v2-b iBims-1, AbsRel / delta1 0.0378 / 0.9834 0.0378 / 0.9834 0.0378 / 0.9834 0.0378 / 0.9834
depth-anything-v2-b ETH3D two-view train left, AbsRel / delta1 0.0696 / 0.9369 0.0698 / 0.9361 0.0696 / 0.9369 0.0696 / 0.9372 possibly in the training data
depth-anything-v2-b Middlebury 2014 trainingH left, AbsRel / delta1 0.0318 / 0.9958 0.0319 / 0.9957 0.0318 / 0.9958 0.0318 / 0.9958 possibly in the training data
depth-anything-v2-l NYUv2 test, AbsRel / delta1 0.0439 / 0.9814 0.0439 / 0.9814 0.0439 / 0.9814 0.0439 / 0.9814
depth-anything-v2-l iBims-1, AbsRel / delta1 0.0347 / 0.9851 0.0347 / 0.9851 0.0347 / 0.9851 0.0347 / 0.9851
depth-anything-v2-l ETH3D two-view train left, AbsRel / delta1 0.0627 / 0.9513 0.0627 / 0.9513 0.0627 / 0.9512 0.0627 / 0.9513 possibly in the training data
depth-anything-v2-l Middlebury 2014 trainingH left, AbsRel / delta1 0.0296 / 0.9961 0.0296 / 0.9961 0.0296 / 0.9961 0.0296 / 0.9961 possibly in the training data
depth-anything-v2-metric-hypersim-s NYUv2 test, AbsRel / delta1 0.0643 / 0.9638 0.0643 / 0.9639 0.0643 / 0.9639 0.0643 / 0.9639
depth-anything-v2-metric-hypersim-s iBims-1, AbsRel / delta1 0.0559 / 0.9700 0.0559 / 0.9701 0.0559 / 0.9700 0.0559 / 0.9700
depth-anything-v2-metric-hypersim-s ETH3D two-view train left, AbsRel / delta1 0.1203 / 0.8637 0.1203 / 0.8637 0.1204 / 0.8636 0.1203 / 0.8637 possibly in the training data
depth-anything-v2-metric-hypersim-s Middlebury 2014 trainingH left, AbsRel / delta1 0.0481 / 0.9861 0.0481 / 0.9861 0.0481 / 0.9861 0.0482 / 0.9860 possibly in the training data
depth-anything-v2-metric-hypersim-b NYUv2 test, AbsRel / delta1 0.0549 / 0.9734 0.0549 / 0.9734 0.0549 / 0.9734 0.0549 / 0.9734
depth-anything-v2-metric-hypersim-b iBims-1, AbsRel / delta1 0.0476 / 0.9792 0.0476 / 0.9792 0.0476 / 0.9792 0.0476 / 0.9792
depth-anything-v2-metric-hypersim-b ETH3D two-view train left, AbsRel / delta1 0.0905 / 0.9235 0.0906 / 0.9238 0.0905 / 0.9235 0.0905 / 0.9235 possibly in the training data
depth-anything-v2-metric-hypersim-b Middlebury 2014 trainingH left, AbsRel / delta1 0.0397 / 0.9938 0.0397 / 0.9938 0.0397 / 0.9938 0.0396 / 0.9939 possibly in the training data
depth-anything-v2-metric-hypersim-l NYUv2 test, AbsRel / delta1 0.0491 / 0.9771 0.0490 / 0.9771 0.0491 / 0.9771 0.0491 / 0.9771
depth-anything-v2-metric-hypersim-l iBims-1, AbsRel / delta1 0.0382 / 0.9838 0.0382 / 0.9838 0.0382 / 0.9838 0.0382 / 0.9838
depth-anything-v2-metric-hypersim-l ETH3D two-view train left, AbsRel / delta1 0.0704 / 0.9586 0.0705 / 0.9586 0.0704 / 0.9585 0.0705 / 0.9586 possibly in the training data
depth-anything-v2-metric-hypersim-l Middlebury 2014 trainingH left, AbsRel / delta1 0.0325 / 0.9954 0.0325 / 0.9954 0.0324 / 0.9954 0.0325 / 0.9954 possibly in the training data
depth-anything-v2-metric-vkitti-s NYUv2 test, AbsRel / delta1 0.1225 / 0.8529 0.1225 / 0.8530 0.1225 / 0.8529 0.1225 / 0.8530
depth-anything-v2-metric-vkitti-s iBims-1, AbsRel / delta1 0.1145 / 0.8774 0.1145 / 0.8775 0.1145 / 0.8774 0.1145 / 0.8773
depth-anything-v2-metric-vkitti-s ETH3D two-view train left, AbsRel / delta1 0.1370 / 0.8210 0.1369 / 0.8214 0.1370 / 0.8210 0.1369 / 0.8210 possibly in the training data
depth-anything-v2-metric-vkitti-s Middlebury 2014 trainingH left, AbsRel / delta1 0.0730 / 0.9566 0.0729 / 0.9566 0.0730 / 0.9566 0.0730 / 0.9565 possibly in the training data
depth-anything-v2-metric-vkitti-b NYUv2 test, AbsRel / delta1 0.1089 / 0.8847 0.1089 / 0.8847 0.1089 / 0.8847 0.1089 / 0.8847
depth-anything-v2-metric-vkitti-b iBims-1, AbsRel / delta1 0.0998 / 0.9086 0.0998 / 0.9085 0.0998 / 0.9085 0.0998 / 0.9085
depth-anything-v2-metric-vkitti-b ETH3D two-view train left, AbsRel / delta1 0.1352 / 0.8311 0.1353 / 0.8310 0.1353 / 0.8311 0.1353 / 0.8311 possibly in the training data
depth-anything-v2-metric-vkitti-b Middlebury 2014 trainingH left, AbsRel / delta1 0.0651 / 0.9781 0.0651 / 0.9780 0.0651 / 0.9780 0.0651 / 0.9780 possibly in the training data
depth-anything-v2-metric-vkitti-l NYUv2 test, AbsRel / delta1 0.0968 / 0.9133 0.0968 / 0.9133 0.0968 / 0.9133 0.0968 / 0.9133
depth-anything-v2-metric-vkitti-l iBims-1, AbsRel / delta1 0.0783 / 0.9399 0.0783 / 0.9399 0.0784 / 0.9399 0.0783 / 0.9399
depth-anything-v2-metric-vkitti-l ETH3D two-view train left, AbsRel / delta1 0.1081 / 0.8993 0.1081 / 0.8992 0.1081 / 0.8992 0.1082 / 0.8991 possibly in the training data
depth-anything-v2-metric-vkitti-l Middlebury 2014 trainingH left, AbsRel / delta1 0.0551 / 0.9836 0.0551 / 0.9836 0.0551 / 0.9837 0.0551 / 0.9837 possibly in the training data
distill-any-depth-s NYUv2 test, AbsRel / delta1 0.0529 / 0.9764 0.0529 / 0.9764 0.0529 / 0.9764 0.0529 / 0.9764
distill-any-depth-s iBims-1, AbsRel / delta1 0.0476 / 0.9701 0.0476 / 0.9701 0.0476 / 0.9701 0.0476 / 0.9701
distill-any-depth-s ETH3D two-view train left, AbsRel / delta1 0.0854 / 0.9094 0.0855 / 0.9092 0.0855 / 0.9093 0.0855 / 0.9093 possibly in the training data
distill-any-depth-s Middlebury 2014 trainingH left, AbsRel / delta1 0.0335 / 0.9947 0.0335 / 0.9947 0.0336 / 0.9947 0.0335 / 0.9947 possibly in the training data
distill-any-depth-b NYUv2 test, AbsRel / delta1 0.0470 / 0.9803 0.0470 / 0.9803 0.0470 / 0.9803 0.0470 / 0.9803
distill-any-depth-b iBims-1, AbsRel / delta1 0.0392 / 0.9817 0.0392 / 0.9816 0.0392 / 0.9817 0.0392 / 0.9817
distill-any-depth-b ETH3D two-view train left, AbsRel / delta1 0.0695 / 0.9386 0.0696 / 0.9382 0.0695 / 0.9386 0.0695 / 0.9386 possibly in the training data
distill-any-depth-b Middlebury 2014 trainingH left, AbsRel / delta1 0.0312 / 0.9963 0.0312 / 0.9963 0.0312 / 0.9963 0.0312 / 0.9963 possibly in the training data
distill-any-depth-l NYUv2 test, AbsRel / delta1 0.0444 / 0.9818 0.0444 / 0.9817 0.0444 / 0.9817 0.0444 / 0.9817
distill-any-depth-l iBims-1, AbsRel / delta1 0.0375 / 0.9832 0.0375 / 0.9832 0.0375 / 0.9832 0.0375 / 0.9832
distill-any-depth-l ETH3D two-view train left, AbsRel / delta1 0.0640 / 0.9537 0.0640 / 0.9537 0.0640 / 0.9537 0.0639 / 0.9537 possibly in the training data
distill-any-depth-l Middlebury 2014 trainingH left, AbsRel / delta1 0.0303 / 0.9962 0.0303 / 0.9962 0.0303 / 0.9962 0.0303 / 0.9962 possibly in the training data

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 468fba10 / 939adfe8 / f2992269+dirty, 2026-11-06 to 2026-11-10.

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| <= 0.5 % and p99 <= 2 % of the reference's median |value| (absolute error of the output inverse_depth).

Limitations

  • Metric checkpoints predict at most max_depth (20 m Hypersim, 80 m Virtual KITTI 2): the head is a sigmoid scaled by it. Each was fine-tuned on one synthetic domain, so indoor / outdoor scenes outside it get a wrong scale.
  • Distill-Any-Depth runs with this family's pipeline (short side 518, aspect kept, as the authors' transformers ports); the authors' demo squashes to 700 x 700. Their Dav2-Teacher-Large-2w-iter checkpoint is not included.

Usage

from fastforks import depth

# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
model = depth.load("depth-anything-v2-b")  # mode="auto": the preferred backend from recorded measurements
result = model("room.jpg")
result.inverse_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: depth-anything-v2-b, depth-anything-v2-l, depth-anything-v2-metric-hypersim-b, depth-anything-v2-metric-hypersim-l, depth-anything-v2-metric-hypersim-s, depth-anything-v2-metric-vkitti-b, depth-anything-v2-metric-vkitti-l, depth-anything-v2-metric-vkitti-s, depth-anything-v2-s, distill-any-depth-b, distill-any-depth-l, distill-any-depth-s.

Kernels backend

depth.load("depth-anything-v2-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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for fastforks/depth-anything-v2

Finetuned
(2)
this model

Collection including fastforks/depth-anything-v2