canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02

pip install "canvit-pytorch>=0.2"

import torch
from PIL import Image
from canvit_pytorch import CanViTForPretraining
from canvit_pytorch.episode import run_episode
from canvit_pytorch.policies import make_policy
from canvit_pytorch.preprocess import preprocess

model = CanViTForPretraining.from_pretrained("canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02").eval()
scene = preprocess(512)(Image.open("scene.jpg").convert("RGB")).unsqueeze(0)  # [1, 3, 512, 512]

# Five glimpses of 128 px, coarse to fine: the full scene, then quadrants.
policy = make_policy("coarse_to_fine", batch_size=1, device=scene.device, num_glimpses=5, canvas_grid_size=32)
with torch.inference_mode():
    steps = run_episode(
        canvit=model.canvit, images=scene, policy=policy, num_glimpses=5, glimpse_size_px=128,
        initial_state=model.init_state(batch_size=1, canvas_grid_size=32),
    )
    canvas = steps[-1].state.canvas
    features = model.canvit.canvas_patch_grid(canvas)  # [1, 32, 32, canvas_dim]: the scene-wide canvas
    teacher_patches = model.predict_teacher_patches(canvas)  # the teacher's features of the whole scene, standardized

@article{berreby2026canvit,
  title={CanViT: Toward Active-Vision Foundation Models},
  author={Berreby, Yoha{\"i}-Eliel and Du, Sabrina and Durand, Audrey and Krishna, B. Suresh},
  year={2026},
  eprint={2603.22570},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2603.22570}
}