Pith Number

pith:GQ7AFIA2

pith:2025:GQ7AFIA2KIS563MEOYXCERTLKJ

not attested not anchored not stored refs resolved

FastVGGT: Training-Free Acceleration of Visual Geometry Transformer

Jiayi Ji, Liujuan Cao, Shengchuan Zhang, Xiawu Zheng, Yansong Qu, You Shen, Zhipeng Zhang

A 3D-specific token partitioning strategy lets token merging accelerate VGGT fourfold on thousand-image sequences without retraining.

arxiv:2509.02560 v2 · 2025-09-02 · 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{GQ7AFIA2KIS563MEOYXCERTLKJ}

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

Notably, with 1000 input images, FastVGGT achieves a 4x speedup over VGGT while mitigating error accumulation in long-sequence scenarios.

C2weakest assumption

That the newly devised 3D-specific token partitioning strategy can remove redundant computation while fully preserving VGGT's reconstruction capacity, even though directly applying existing merging techniques is stated to be challenging due to architectural and task-specific properties.

C3one line summary

FastVGGT achieves 4x speedup on VGGT for 1000-image inputs using training-free token merging tailored to 3D architectures while reducing error accumulation.

References

33 extracted · 33 resolved · 8 Pith anchors

[1] Token merging for fast sta- ble diffusion

[2] Token Merging: Your ViT But Faster 2022 · arXiv:2210.09461

[3] Pumer: Pruning and merging tokens for efficient vision language models.arXiv preprint arXiv:2305.17530,

[4] Emerg- ing properties in self-supervised vision transformers 2021

[5] vid-tldr: Training free token merging for light-weight video transformer 2024

Formal links

3 machine-checked theorem links

Cited by

24 papers in Pith

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

Receipt and verification

First computed	2026-05-17T23:38:49.752098Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

343e02a01a5225df6d84762e22466b52617a475fbcaf461a2972c81236a1a4b4

Aliases

arxiv: 2509.02560 · arxiv_version: 2509.02560v2 · doi: 10.48550/arxiv.2509.02560 · pith_short_12: GQ7AFIA2KIS5 · pith_short_16: GQ7AFIA2KIS563ME · pith_short_8: GQ7AFIA2

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/GQ7AFIA2KIS563MEOYXCERTLKJ \
  | 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: 343e02a01a5225df6d84762e22466b52617a475fbcaf461a2972c81236a1a4b4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b5183e4a8ae8fe8f06347e2d74565b2c0c9067442ce470bb14af321b1d5f9d74",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-09-02T17:54:21Z",
    "title_canon_sha256": "775dee16a98c51d2dca3277c76c502537f8c521554eeb5ce1246ba918d1be400"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.02560",
    "kind": "arxiv",
    "version": 2
  }
}