pith. sign in
Pith Number

pith:LG6XRG7D

pith:2025:LG6XRG7DALQ6CQZT6JR2VC4X5K
not attested not anchored not stored refs resolved

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Dehu Wang, Ding Liang, Wanli Ouyang, Xingchao Liu, Yangguang Li, Yan-Pei Cao, Yuan-Chen Guo, Yuan Liang, Zexiang Liu, Zhipeng Yu, Zi-Xin Zou

TripoSG generates high-fidelity 3D meshes from images via a large-scale rectified flow transformer trained on two million samples.

arxiv:2502.06608 v3 · 2025-02-10 · cs.CV · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LG6XRG7DALQ6CQZT6JR2VC4X5K}

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

TripoSG achieves state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images with strong generalization across diverse image styles and contents.

C2weakest assumption

The assumption that the custom data processing pipeline produces sufficiently high-quality, diverse, and representative 3D samples at the claimed scale of 2 million without introducing biases or artifacts that would limit generalization or fidelity in real-world use.

C3one line summary

TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.

References

187 extracted · 187 resolved · 13 Pith anchors

[1] Frozen in time: A joint video and image encoder for end-to-end retrieval 2021
[2] All are worth words: A vit backbone for diffusion models 2023
[4] blackforestlabs. Flux. https://github.com/black-forest-labs/flux, 2024 2024
[5] Video generation models as world simulators 2024
[6] R., Nagano, K., Chan, M 2023

Formal links

2 machine-checked theorem links

Cited by

30 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:46.470101Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

59bd789be302e1e14333f263aa8b97eab554a7fea072cc8d62dc0236713469b6

Aliases

arxiv: 2502.06608 · arxiv_version: 2502.06608v3 · doi: 10.48550/arxiv.2502.06608 · pith_short_12: LG6XRG7DALQ6 · pith_short_16: LG6XRG7DALQ6CQZT · pith_short_8: LG6XRG7D
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LG6XRG7DALQ6CQZT6JR2VC4X5K \
  | 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: 59bd789be302e1e14333f263aa8b97eab554a7fea072cc8d62dc0236713469b6
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "b5b4e235d2ba8825bfb771cabdf662fbd289b46f55f20e3714d6c1382c6898c1",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-02-10T16:07:54Z",
    "title_canon_sha256": "5af621890d5e288d22d2defea32177771807c7d11f9e35f1eec1d4ab317e14d3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.06608",
    "kind": "arxiv",
    "version": 3
  }
}