FaceFill

dabanba/FaceFill

FaceFill is a other model from dabanba. Use it for the other task on the model card, and read the license before you ship it in a product. It is set up for onnx. The card lists the license as mit.

Causal GRU that predicts 11 upper-face ARKit morphs (brows / eyes / blinks) from 30 lower-face channels when an HMD occludes the upper face.

Downloads · 30 days

Access

Public

Updated Jul 24, 2026

Repo size

13.3 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.onnx13.3 MB · 100%

At a glance

Task: other
Library: onnx
License: mit
Access: Public
Created: Jul 24, 2026
Updated: Jul 24, 2026
SHA: 2d0b3c8a

Model card

From the Hugging Face model README

FaceFill

Causal GRU that predicts 11 upper-face ARKit morphs (brows / eyes / blinks) from 30 lower-face channels when an HMD occludes the upper face.

~3.36M params · streaming step with GRU hidden state.

Files

File	Description
`model.onnx`	Stateful single-frame step (opset 17)
`eval.json`	Autoregressive test metrics (held-out MEAD W009)

Inputs / outputs

Inputs

Name	Shape	Meaning
`current`	`[B, 80]`	lower + vel + head + conf + blink state
`history`	`[B, 176]`	prior full morphs + vel + obs mask + …
`u_prev`	`[B, 11]`	previous upper prediction
`hidden_in`	`[3, B, 384]`	GRU hidden

Outputs

Name	Shape
`u_hat`	`[B, 11]`
`u_abs`	`[B, 11]`
`u_delta`	`[B, 11]`
`blink_onset_logits`	`[B, 3]`
`blink_duration`	`[B]`
`blink_amplitude`	`[B]`
`hidden_out`	`[3, B, 384]`

Combine rule: û = clamp(α·(u_prev + Δu) + (1−α)·u_abs), α=0.8.

Training data

Features derived from MEAD frontal videos via MediaPipe Face Landmarker (person-disjoint M033 / W015 / W009 for this release). Does not redistribute MEAD videos.

Eval (AR, test)

mean MAE 0.075
mean Pearson 0.82
blink F1 0.73

Usage

import onnxruntime as ort
import numpy as np

sess = ort.InferenceSession("model.onnx")
B = 1
feeds = {
    "current": np.zeros((B, 80), np.float32),
    "history": np.zeros((B, 176), np.float32),
    "u_prev": np.zeros((B, 11), np.float32),
    "hidden_in": np.zeros((3, B, 384), np.float32),
}
outs = sess.run(None, feeds)
# u_hat, u_abs, u_delta, blink_onset_logits, blink_duration, blink_amplitude, hidden_out

Browser / WebXR companion: load with ONNX Runtime Web (see FaceFill / WebXREmotion projects).

License

MIT (this model). Respect MEAD terms for any further training on that dataset.

Task: other
Library: onnx
License: mit
Created: Jul 24, 2026
Updated: Jul 24, 2026