pith:F5237LHX
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
Unifying geometric guidance at representation, architecture, and loss levels lets video models edit images under new camera poses with less drift.
arxiv:2604.17565 v3 · 2026-04-19 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{F5237LHXARUSC2ZJVR5HVMR54T}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Comprehensive experiments across multiple public benchmarks, encompassing both extensive and limited camera motion settings, demonstrate that UniGeo significantly outperforms existing methods in both visual quality and geometric consistency.
That fragmented geometric guidance is the primary cause of drift and that injecting unified guidance at representation, architecture, and loss levels will jointly stabilize output without new inconsistencies or the need for extensive hyperparameter tuning.
UniGeo unifies geometric guidance across three levels in video models to reduce geometric drift and improve consistency in camera-controllable image editing.
Receipt and verification
| First computed | 2026-06-26T01:15:51.883404Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
2f75bfacf70469216b29ac7a7ab23de4ebea4db9729719515e94c8a893a94702
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/F5237LHXARUSC2ZJVR5HVMR54T \
| 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: 2f75bfacf70469216b29ac7a7ab23de4ebea4db9729719515e94c8a893a94702
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e9189205291db49b9e48fddaf9989a2f86790cc91e50b8edc93f05bb4dee7714",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-19T18:11:08Z",
"title_canon_sha256": "720c693f3433446380308424a4e4891c4712dfe1e83a747eb313b10de50f1974"
},
"schema_version": "1.0",
"source": {
"id": "2604.17565",
"kind": "arxiv",
"version": 3
}
}