Pith Number

pith:LXGHW2BG

pith:2023:LXGHW2BGAMI2D4MGOGDQHCFKV2

not attested not anchored not stored refs resolved

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Cheng Lin, Lingjie Liu, Taku Komura, Wenping Wang, Xiaoxiao Long, Yuan Liu, Zijiao Zeng

SyncDreamer generates multiple consistent views of an object from one input image by synchronizing their diffusion process.

arxiv:2309.03453 v2 · 2023-09-07 · cs.CV · cs.AI · cs.GR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LXGHW2BGAMI2D4MGOGDQHCFKV2}

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

SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D.

C2weakest assumption

The 3D-aware feature attention mechanism successfully correlates corresponding features across views without introducing new inconsistencies or artifacts during the joint reverse diffusion process.

C3one line summary

SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.

References

46 extracted · 46 resolved · 7 Pith anchors

[1] Re-imagine the negative prompt algorithm: Transform 2d diffusion into 3d, alleviate janus problem and beyond

[2] Multidiffusion: Fusing diffusion paths for controlled image generation

[3] ShapeNet: An Information-Rich 3D Model Repository · arXiv:1512.03012

[4] Single- stage diffusion nerf: A unified approach to 3d generation and reconstruction

[5] Objaverse-XL: A Universe of 10M+ 3D Objects 2024 · arXiv:2307.05663

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Stream3D: Sequential Multi-View 3D Generation via Evidential Memory

Functionalization via Structure Completion and Motion Rectification

Receipt and verification

First computed	2026-05-17T23:38:48.177841Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5dcc7b68260311a1f18671870388aaae97b3014e62c7c141ea4c18597b849318

Aliases

arxiv: 2309.03453 · arxiv_version: 2309.03453v2 · doi: 10.48550/arxiv.2309.03453 · pith_short_12: LXGHW2BGAMI2 · pith_short_16: LXGHW2BGAMI2D4MG · pith_short_8: LXGHW2BG

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/LXGHW2BGAMI2D4MGOGDQHCFKV2 \
  | 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: 5dcc7b68260311a1f18671870388aaae97b3014e62c7c141ea4c18597b849318

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6ffd95ba3b94bbd19c6b9c09224aaf9a7a93456fad07c7adb222496d882b3eed",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.GR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-09-07T02:28:04Z",
    "title_canon_sha256": "c0bc6d4229afcbf80b4af494079b0f0bced3c98ab03cc885eaa2619d13f72c6c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2309.03453",
    "kind": "arxiv",
    "version": 2
  }
}