Pith Number

pith:TQIHEVKT

pith:2026:TQIHEVKTCMXGFPQOUJFI6XN6C2

not attested not anchored not stored refs pending

MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

Dao Thien Phong, Dongze Lian, Guanli Hou, Hanwang Zhang, Kehong Gong, Mingxi Xu, Mingyuan Zhang, Ning Zhang, Qi Wang, Weixia He, Xiaoyu He, Zhengyu Li, Zhengyu Wen

A reference pose-rotation pair anchors rotation learning so that video-to-pose and pose-to-rotation stages can be trained end-to-end for any skeleton.

arxiv:2604.28130 v3 · 2026-04-30 · 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{TQIHEVKTCMXGFPQOUJFI6XN6C2}

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

we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized... Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines.

C2weakest assumption

That supplying one reference pose-rotation pair from the target asset, together with the rest pose, is sufficient to uniquely anchor the rotation coordinate system and enable effective learning across arbitrary unseen skeletons without additional constraints or post-processing.

C3one line summary

A fully differentiable end-to-end model for arbitrary-skeleton motion capture from video that jointly learns pose estimation and rotation recovery using reference pose-rotation pairs to eliminate IK ambiguities.

Cited by

2 papers in Pith

AnyAct: Towards Human Reenactment of Character Motion From Video

Receipt and verification

First computed	2026-06-23T01:12:07.786075Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36

Aliases

arxiv: 2604.28130 · arxiv_version: 2604.28130v3 · doi: 10.48550/arxiv.2604.28130 · pith_short_12: TQIHEVKTCMXG · pith_short_16: TQIHEVKTCMXGFPQO · pith_short_8: TQIHEVKT

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/TQIHEVKTCMXGFPQOUJFI6XN6C2 \
  | 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: 9c10725553132e62be0ea24a8f5dbe169251f1c6460149e869c65a0766430e36

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cd97f7be77a3cc9ba7da53d1d89d6ebd75215559d540f8505b759410c1c6863c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-30T17:16:38Z",
    "title_canon_sha256": "8fe5d93a1a05045be4b6b0ef06cd2d0f8ca80d829a6350895c30f3687f1b02d8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.28130",
    "kind": "arxiv",
    "version": 3
  }
}