Pith Number

pith:KL45WMUM

pith:2026:KL45WMUMJ2W6BGCCHJPPEVL3U5

not attested not anchored not stored refs resolved

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

Bingbing Liu, Chengjie Huang, David Huang, Dongfeng Bai, Guile Wu

TurboVGGT speeds multi-view 3D reconstruction by learning varying sparsity in attention across frames and layers.

arxiv:2605.14315 v1 · 2026-05-14 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KL45WMUMJ2W6BGCCHJPPEVL3U5}

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

TurboVGGT achieves fast multi-view reconstruction while maintaining competitive reconstruction quality compared with state-of-the-art methods.

C2weakest assumption

The assumption that adaptively learning representative tokens with varying sparsity levels across frames, layers, and structurally informative regions will reliably capture global relationships without losing critical geometric details in diverse real-world scenes.

C3one line summary

TurboVGGT uses adaptive sparse global attention with varying sparsity levels across frames and layers plus frame attention to enable faster multi-view 3D reconstruction while keeping competitive quality versus prior state-of-the-art methods.

References

54 extracted · 54 resolved · 2 Pith anchors

[1] Mapillary planet-scale depth dataset 2020

[2] Scene- script: Reconstructing scenes with an autoregressive structured language model 2024

[3] Neural rgb-d surface reconstruction 2022

[4] Token merging: Your vit but faster 2023

[5] A naturalistic open source movie for optical flow evaluation 2012

Receipt and verification

First computed	2026-05-17T23:39:09.905428Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

52f9db328c4eade098423a5ef2557ba74940707614afe1352b13c3b3307e9f89

Aliases

arxiv: 2605.14315 · arxiv_version: 2605.14315v1 · doi: 10.48550/arxiv.2605.14315 · pith_short_12: KL45WMUMJ2W6 · pith_short_16: KL45WMUMJ2W6BGCC · pith_short_8: KL45WMUM

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/KL45WMUMJ2W6BGCCHJPPEVL3U5 \
  | 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: 52f9db328c4eade098423a5ef2557ba74940707614afe1352b13c3b3307e9f89

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "831cda8484bd628f8a5135b3999062c1115841ad209086668e028b944115fa15",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T03:24:09Z",
    "title_canon_sha256": "28ec58e343c854ab448e2b5a731c91a40049bf1c163053032dd5760388681c72"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14315",
    "kind": "arxiv",
    "version": 1
  }
}