Pith Number

pith:5P5GJZVE

pith:2026:5P5GJZVE42FIYASUZMZM6RYYMP

not attested not anchored not stored refs resolved

HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation

Ajay Waghumbare, Ashish Musale, Upasna Singh, Vinduja Thekkath

3D human pose estimation performed inside hyperbolic space preserves the skeleton's tree structure and avoids the volume distortion that Euclidean methods produce.

arxiv:2605.10100 v2 · 2026-05-11 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5P5GJZVE42FIYASUZMZM6RYYMP}

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

HYPERPOSE achieves state-of-the-art structural and temporal coherence, significantly reducing both volume distortion and velocity error, while establishing new state-of-the-art benchmarks in overall positional accuracy.

C2weakest assumption

That operating entirely within the Lorentz model of hyperbolic space will natively preserve the hierarchical tree topology of the human skeleton and avoid the exponential volume distortion that Euclidean methods suffer from. (Abstract, opening motivation paragraph)

C3one line summary

HYPERPOSE performs 3D human pose estimation entirely in the Lorentz hyperbolic model using kinematic phase-space attention and Riemannian losses, reporting state-of-the-art structural coherence on Human3.6M and MPI-INF-3DHP.

References

29 extracted · 29 resolved · 0 Pith anchors

[1] Catalin Ionescu, Dragos Papava, Vlad Olaru, and Cristian Sminchisescu. Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments.IEEE Transactions on Pattern 2014

[2] Cascaded pyramid network for multi-person pose estimation 2018

[3] Julieta Martinez, Rayat Hossain, Javier Romero, and James J. Little. A simple yet effective baseline for 3D human pose estimation. InProceedings of the IEEE International Conference on Computer Vision 2017

[4] 3D human pose estimation = 2D pose estimation + matching 2019

[5] 3D human pose estimation with spatial and temporal transformers 2021

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:42.400914Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ebfa64e6a4e68a8c0254cb32cf471863d0b2d1ba6d4126edc0f702cf50b45906

Aliases

arxiv: 2605.10100 · arxiv_version: 2605.10100v2 · doi: 10.48550/arxiv.2605.10100 · pith_short_12: 5P5GJZVE42FI · pith_short_16: 5P5GJZVE42FIYASU · pith_short_8: 5P5GJZVE

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/5P5GJZVE42FIYASUZMZM6RYYMP \
  | 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: ebfa64e6a4e68a8c0254cb32cf471863d0b2d1ba6d4126edc0f702cf50b45906

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "436da024e54b9e8aedb661e89cea68561dfe401ac8d0fbab681a09ef582ae0d2",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-11T07:17:32Z",
    "title_canon_sha256": "86e681bb5597699b83f8f6e78d76df9b51c6c8506afd326a0c45ab2f562fc45d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10100",
    "kind": "arxiv",
    "version": 2
  }
}