metadata
license: apache-2.0
library_name: transformers
base_model: []
tags:
- gaze-estimation
- gaze-target-estimation
- dinov3
pipeline_tag: image-feature-extraction
PaGE-ViT-B
Base variant, general scenes. Distilled. Part of the PaGE gaze target estimation family.
- Backbone: DINOv3 ViT-B/16
- Params: ~90M
- Scene input: 512×512, Head input: 256×256, Heatmap output: 64×64
- Source checkpoint:
vitb_distill.pt
Self-contained weights
This checkpoint includes the full DINOv3 backbone weights in its safetensors files. No external
DINOv3 weights are downloaded. The model code (modeling_page.py) is loaded automatically from
Octopus1/PaGE via auto_map when you pass trust_remote_code=True.
Installation
pip install torch torchvision timm "transformers>=4.56" safetensors pillow
Usage
from transformers import AutoModel, AutoImageProcessor
from PIL import Image
import torch
repo = "Octopus1/page-vitb"
model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval()
processor = AutoImageProcessor.from_pretrained(repo, trust_remote_code=True)
scene = Image.open("scene.jpg").convert("RGB")
head = Image.open("head.jpg").convert("RGB")
inputs = processor(scene, head_crops=[head], bboxes=[[(0.10, 0.10, 0.30, 0.40)]])
with torch.no_grad():
out = model(inputs)
heatmap = out["heatmap"][0] # [Np, 64, 64]
inout = out["inout"][0] # [Np]
Inputs / Outputs
See the family README for the full input/output spec.
- Input dict:
images(list of[B,3,512,512]),head_images(list of[sum(Np),3,256,256]),bboxes(per-image list of(xmin,ymin,xmax,ymax)in[0,1]). - Output dict:
heatmap(list of[Np,64,64], sigmoid),inout(list of[Np], sigmoid).
License
Apache-2.0.