{
  "annotation_id": "954c9e74-a793-4099-aa92-4a408346e547",
  "date_created": "2026-02-17T05:53:19.998000Z",
  "date_modified": "2026-02-17T05:53:19.998000Z",
  "file_hash": "b656300bb64c537837b9b3b59c092631339f5d4b46d4f96996d3a672e9693586",
  "private": false,
  "record": {
    "abstract": "Image registration under domain shift remains a fundamental challenge in computer vision and medical imaging: when source and target images exhibit systematic intensity differences, the brightness constancy assumption underlying conventional registration methods is violated, rendering correspondence estimation ill-posed. We propose SAR-Net, a unified framework that addresses this challenge through principled scene-appearance disentanglement. Our key insight is that observed images can be decomposed into domain-invariant scene representations and domain-specific appearance codes, enabling registration via re-rendering rather than direct intensity matching. We establish theoretical conditions under which this decomposition enables consistent cross-domain alignment (Proposition 1) and prove that our scene consistency loss provides a sufficient condition for geometric correspondence in the shared latent space (Proposition 2). Empirically, we validate SAR-Net on bidirectional scanning microscopy, where coupled domain shift and geometric distortion create a challenging real-world testbed. Our method achieves 0.885 SSIM and 0.979 NCC, representing 3.1x improvement over the strongest baseline, while maintaining real-time performance (77 fps). Ablation studies confirm that both scene consistency and domain alignment losses are necessary: removing either degrades performance by 90% SSIM or causes 223x increase in latent alignment error, respectively. Code and data are available at https://github.com/D-ST-Sword/SAR-NET.",
    "arxiv_id": "2601.08875",
    "authors": [
      "Jiahao Qin",
      "Yiwen Wang"
    ],
    "categories": [
      "cs.CV",
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Learning Domain-Invariant Representations for Cross-Domain Image Registration via Scene-Appearance Disentanglement",
    "url": "https://arxiv.org/abs/2601.08875",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "dbd1debe-ae39-4ea0-b1b4-ce853b155af2",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}