Pith Number

pith:E77H2NAC

pith:2026:E77H2NACZRVFLXQESASVSSO727

not attested not anchored not stored refs resolved

Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery

Buzhen Huang, Chongyang Xu, Kun Li, Minghao Sun, Yitao Xie

A shared-topology hypergraph fuses RGB, geometric and pose cues to recover 3D crowd meshes despite heavy occlusion.

arxiv:2605.13854 v1 · 2026-04-01 · cs.CV · cs.GR · cs.MM · eess.IV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{E77H2NACZRVFLXQESASVSSO727}

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

Extensive experiments on the Panoptic and GigaCrowd benchmarks confirm that our method achieves new state-of-the-art performance.

C2weakest assumption

The shared-topology hypergraph and hypergraph-based contrastive learning scheme can effectively model higher-order crowd dynamics and enforce cross-modal orthogonality to infer missing information under severe occlusion.

C3one line summary

Contrastive multi-modal hypergraph reasoning fuses semantic, geometric, and pose cues to achieve state-of-the-art 3D crowd mesh recovery under severe occlusions.

References

43 extracted · 43 resolved · 1 Pith anchors

[1] Dycrowd: Towards dynamic crowd reconstruction from a large-scene video, 2025

[2] Crowd3d: Towards hundreds of people reconstruction from a single image, 2023

[3] Reconstructing groups of people with hypergraph relational reasoning, 2023

[4] Closely interactive human reconstruction with proxemics and physics-guided adaption, 2024

[5] Reconstructing close human interaction with appearance and proxemics reasoning, 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:19.568560Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

27fe7d3402cc6a55de0490255949dfd7f05a1d5f069b68c27ae21a0f0354c9ad

Aliases

arxiv: 2605.13854 · arxiv_version: 2605.13854v1 · doi: 10.48550/arxiv.2605.13854 · pith_short_12: E77H2NACZRVF · pith_short_16: E77H2NACZRVFLXQE · pith_short_8: E77H2NAC

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/E77H2NACZRVFLXQESASVSSO727 \
  | 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: 27fe7d3402cc6a55de0490255949dfd7f05a1d5f069b68c27ae21a0f0354c9ad

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "070d2abfd40f5d5e175c06dea7523942e2faa09a809db0d2c8b8b92d9cc5c7e8",
    "cross_cats_sorted": [
      "cs.GR",
      "cs.MM",
      "eess.IV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-01T09:39:01Z",
    "title_canon_sha256": "9ef67c37f46fc39e1c822aa1550f83cbd0543043d3b4ef9615f43a07bb150eae"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13854",
    "kind": "arxiv",
    "version": 1
  }
}