Pith Number

pith:6NIQKDSF

pith:2026:6NIQKDSFOSW3JHRJF32XEJI5US

not attested not anchored not stored refs resolved

CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration

Mengzhu Ding, Xichao Teng, Xuecong Liu, Zhang Li, Zixuan Sun

CRFT uses a transformer to learn a consistent recurrent feature flow that aligns cross-modal images more accurately and robustly than existing methods.

arxiv:2604.05689 v1 · 2026-04-07 · cs.CV · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6NIQKDSFOSW3JHRJF32XEJI5US}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

CRFT consistently outperforms state-of-the-art registration methods in both accuracy and robustness.

C2weakest assumption

That a single modality-independent feature flow representation learned in a transformer can jointly handle feature alignment and flow estimation while the iterative discrepancy-guided attention with Spatial Geometric Transform enforces consistency under large affine and scale variations.

C3one line summary

CRFT is a new transformer architecture using recurrent consistent feature flow learning to achieve accurate and robust cross-modal image registration under large variations.

References

66 extracted · 66 resolved · 0 Pith anchors

[1] Deep learning models for digital image processing: a review.Artificial Intelligence Review, 57(1):11 2024

[2] Graphi2p: Image-to-point cloud registration with exploring pattern of correspondence via graph learning 2025

[3] A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond.Medical Image Analysis, 100:103385

[4] Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images 2024

[5] Dsap: Dynamic sparse attention perception matcher for accurate local feature matching 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-30T02:18:08.151128Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f351050e4574adb49e292ef572251da4bb3724265d4f0ab70d8e158c903360df

Aliases

arxiv: 2604.05689 · arxiv_version: 2604.05689v1 · doi: 10.48550/arxiv.2604.05689 · pith_short_12: 6NIQKDSFOSW3 · pith_short_16: 6NIQKDSFOSW3JHRJ · pith_short_8: 6NIQKDSF

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/6NIQKDSFOSW3JHRJF32XEJI5US \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f351050e4574adb49e292ef572251da4bb3724265d4f0ab70d8e158c903360df

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "09cd875eb0e73572935920e3e662d2ea29577bdd4cac5262791b25635e48cad7",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-07T10:40:27Z",
    "title_canon_sha256": "cc48b7e54d393b0777d6f02aa9d23aa590570315da226405be64278dd018b994"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.05689",
    "kind": "arxiv",
    "version": 1
  }
}