Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
The
coreai-model-zoo
's first depth model.
Monocular (single-image)
relative depth
estimation running fully on-device on Apple's Core AI
runtime, as a single static
.aimodel
. A conversion of ByteDance's
Depth Anything 3
(
depth-anything/DA3-SMALL
/
DA3-BASE
, Apache-2.0): a DINOv2 ViT backbone +
DPT-style head. Drop in an RGB image, get a depth map (and a confidence map). No NMS, no sampling —
host post-processing is just a colormap.
Bundles
dir
variant
params
dtype
size
M4 Max GPU
small/da3-small_float16.aimodel
ViT-S
34.3M
fp16
54 MB
65.7 FPS
small/da3-small_float32.aimodel
ViT-S
34.3M
fp32
105 MB
56.5 FPS
base/da3-base_float16.aimodel
ViT-B
135.4M
fp16
202 MB
26.5 FPS
base/da3-base_float32.aimodel
ViT-B
135.4M
fp32
402 MB
23.0 FPS
small · fp16
is the on-device hero — 54 MB, 65 FPS at 504² on an M4 Max, comfortably real-time on
iPhone-class GPUs. Each
.aimodel
is a directory bundle (
main.mlirb
+
metadata.json
).
I/O contract
input : image [1, 3, 504, 504] RGB, raw [0, 1] (ImageNet normalization is folded into the graph)
output: depth [1, 504, 504] relative depth (exp-activated; larger = nearer)
depth_conf [1, 504, 504] confidence
Host: resize the RGB image to 504 × 504 (e.g. cv2
INTER_AREA
), feed raw [0, 1], run, then resize
the depth map back to the original H × W. For display, the DA3 convention is inverse-depth →
percentile 2–98 normalize →
Spectral
colormap.
Fidelity
Bit-exact conversion:
the Core AI engine matches the PyTorch reference at
cos 1.000000
(≤
~1e-5 / ~1e-2 per-pixel for fp32 / fp16) on both CPU and GPU, at any fixed input shape.
vs the official DA3 viewer:
mean Pearson r ≈ 0.98
across diverse aspect ratios (square
inputs r = 1.000) — within DA3's own resolution sensitivity (its 504-vs-518 outputs differ by
r ≈ 0.975–0.984).
Usage (CoreAIKit / coreai.runtime)
import coreai.runtime as rt, numpy as np
from PIL import Image
m = await rt.AIModel.load("small/da3-small_float16.aimodel",
rt.SpecializationOptions.from_preferred_compute_unit_kind(rt.ComputeUnitKind.gpu()))
fn = m.load_function("main")
img = np.asarray(Image.open("photo.jpg").convert("RGB").resize((504, 504)))
x = (img.astype(np.float16) / 255.0).transpose(2, 0, 1)[None] # raw [0,1], NCHW
depth = (await fn({"image": rt.NDArray(x)}))["depth"].numpy().reshape(504, 504)
Depth-Anything-3-CoreAI huggingface.co is an AI model on huggingface.co that provides Depth-Anything-3-CoreAI's model effect (), which can be used instantly with this mlboydaisuke Depth-Anything-3-CoreAI model. huggingface.co supports a free trial of the Depth-Anything-3-CoreAI model, and also provides paid use of the Depth-Anything-3-CoreAI. Support call Depth-Anything-3-CoreAI model through api, including Node.js, Python, http.
Depth-Anything-3-CoreAI huggingface.co is an online trial and call api platform, which integrates Depth-Anything-3-CoreAI's modeling effects, including api services, and provides a free online trial of Depth-Anything-3-CoreAI, you can try Depth-Anything-3-CoreAI online for free by clicking the link below.
mlboydaisuke Depth-Anything-3-CoreAI online free url in huggingface.co:
Depth-Anything-3-CoreAI is an open source model from GitHub that offers a free installation service, and any user can find Depth-Anything-3-CoreAI on GitHub to install. At the same time, huggingface.co provides the effect of Depth-Anything-3-CoreAI install, users can directly use Depth-Anything-3-CoreAI installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Depth-Anything-3-CoreAI install url in huggingface.co: