pith. sign in
Pith Number

pith:AR3M4W6X

pith:2025:AR3M4W6XY6G7FETDUFTTYHWR2J
not attested not anchored not stored refs resolved

VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences

Jian Yang, Jiawei Xu, Jin Xie, Kai Deng, Zexin Ti

By dividing long video sequences into chunks and aligning their overlaps with lightweight loop closure, a foundation 3D model can produce accurate monocular reconstructions and trajectories over kilometer-scale outdoor paths without camera,

arxiv:2507.16443 v2 · 2025-07-22 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AR3M4W6XY6G7FETDUFTTYHWR2J}

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

VGGT-Long achieves trajectory and reconstruction performance comparable to traditional methods on KITTI, Waymo, and Virtual KITTI datasets without requiring camera calibration, depth supervision or model retraining.

C2weakest assumption

That chunk-wise alignment plus lightweight loop closure will maintain global consistency and metric accuracy over kilometer-scale trajectories without drift or scale drift that would require additional constraints or supervision.

C3one line summary

VGGT-Long extends VGGT with chunking, overlap alignment, and loop closure to produce consistent kilometer-scale 3D reconstructions from monocular RGB sequences without retraining or extra supervision.

References

47 extracted · 47 resolved · 0 Pith anchors

[1] Building rome in a day.Communications of the ACM, 54 (10):105–112, 2011 2011
[2] Learning to match features with seeded graph matching network 2021
[3] Soft2: Stereo visual odometry for road vehicles based on a point- to-epipolar-line metric.IEEE Transactions on Robotics, 39 (1):273–288, 2022 2022
[4] FlashAttention-2: Faster attention with better par- allelism and work partitioning 2024
[5] Fu, Stefano Ermon, Atri Rudra, and Christopher R´e 2022

Formal links

2 machine-checked theorem links

Cited by

23 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:14.546444Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0476ce5bd7c78df29263a1673c1ed1d25f27281a074fa9d77ae8f2d02c4c04a9

Aliases

arxiv: 2507.16443 · arxiv_version: 2507.16443v2 · doi: 10.48550/arxiv.2507.16443 · pith_short_12: AR3M4W6XY6G7 · pith_short_16: AR3M4W6XY6G7FETD · pith_short_8: AR3M4W6X
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AR3M4W6XY6G7FETDUFTTYHWR2J \
  | 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: 0476ce5bd7c78df29263a1673c1ed1d25f27281a074fa9d77ae8f2d02c4c04a9
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "99eefb1edc7b986d451325d37c3696082d8772fa2cbb54fe83b131ac28524973",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-07-22T10:39:04Z",
    "title_canon_sha256": "9108ac9099651f5f1c40ea91e45191e003e1c2b5af5308b7771eddf8c9a52abd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.16443",
    "kind": "arxiv",
    "version": 2
  }
}