Cornelius — CCG Card Corner Detector

MobileViT-XXS backbone with a SimCC coordinate classification head, trained to locate the four corners of a CCG card (Magic: The Gathering, Pokémon, etc.) in a photograph or video frame.

Model details

Property	Value
Architecture	MobileViT-XXS + SimCC head
Input	384×384 RGB, ImageNet-normalised
Outputs	corners (8 floats, normalised [0,1]), presence logit, sharpness scalar
Parameters	~1.82M
File size	8.6 MB (fp32 ONNX)
Codename	cornelius
Version	1.0.0 (epoch 45)

Outputs

• corners — 8 floats [x0,y0, x1,y1, x2,y2, x3,y3] in TL→TR→BR→BL order, normalised [0,1]
• presence — raw logit; unreliable on blank images, prefer the sharpness gate
• sharpness — mean peak of the 8 SimCC softmax distributions; blank frames ≈ 0.008, valid cards ≈ 0.03–0.07

Usage

The easiest way to use Cornelius is through the CollectorVision library, which wires it into a full detect → dewarp → embed → identify pipeline:

import collector_vision as cvg

cvid = cvg.Identifier(cvg.HFD("HanClinto/milo", "scryfall-mtg"))
result = cvid.identify("photo.jpg")
print(result.ids)  # {"scryfall_id": "..."}

Direct ONNX usage

import onnxruntime as ort
import numpy as np
from PIL import Image

session = ort.InferenceSession("model.onnx")

# Preprocess: resize to 384×384, ImageNet normalise, NCHW float32
img = Image.open("photo.jpg").convert("RGB").resize((384, 384))
x = np.array(img, dtype=np.float32) / 255.0
x = (x - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]
x = x.transpose(2, 0, 1)[None]  # (1, 3, 384, 384)

corners, presence, sharpness = session.run(None, {"pixel_values": x})
# corners: (1, 8) — x0,y0,x1,y1,x2,y2,x3,y3 normalised [0,1], TL→TR→BR→BL
# presence: (1, 1) — raw logit
# sharpness: (1, 1) — use > 0.02 as a card-present gate

if sharpness[0, 0] > 0.02:
    pts = corners[0].reshape(4, 2)  # (4, 2) normalised corners

Part of CollectorVision

Used together with HanClinto/milo in the CollectorVision inference library.