Pith Number

pith:5JNWYONU

pith:2025:5JNWYONUGII27LNWQVRNSLDRDX

not attested not anchored not stored refs pending

Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals

Hojoon Shin, Ki Myung Brian Lee, Nikolay Atanasov, Yulun Tian, Zhirui Dai

Signed directional distance functions learn scene geometry from ellipsoid priors plus neural residuals to give direct, view-dependent distances.

arxiv:2503.20066 v2 · 2025-03-25 · cs.RO · 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{5JNWYONUGII27LNWQVRNSLDRDX}

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

SDDF achieves accurate geometric reconstruction and efficient differentiable directional distance prediction. ... we develop a differentiable hybrid representation that combines explicit ellipsoid priors and implicit neural residuals. This allows the model to handle distance discontinuities around obstacle boundaries effectively while preserving the ability for dense high-fidelity distance prediction.

C2weakest assumption

That the combination of explicit ellipsoid priors with neural residuals is sufficient to handle distance discontinuities at obstacle boundaries without introducing artifacts or requiring extensive per-scene tuning (abstract, paragraph on hybrid representation).

C3one line summary

Proposes SDDF, a hybrid explicit ellipsoid plus neural residual representation for efficient scene-level signed directional distance prediction with claimed competitive accuracy and better geometric consistency than NeRF or Gaussian Splatting.

Receipt and verification

First computed	2026-05-25T02:01:03.143372Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ea5b6c39b43211afadb68562d92c711dfa3d4e77ca002a8485c10ac62cd56faf

Aliases

arxiv: 2503.20066 · arxiv_version: 2503.20066v2 · doi: 10.48550/arxiv.2503.20066 · pith_short_12: 5JNWYONUGII2 · pith_short_16: 5JNWYONUGII27LNW · pith_short_8: 5JNWYONU

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/5JNWYONUGII27LNWQVRNSLDRDX \
  | 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: ea5b6c39b43211afadb68562d92c711dfa3d4e77ca002a8485c10ac62cd56faf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "793c103869c03856c78fb23f67112e6854dc02047766277dfa5214026ef1242d",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-03-25T21:01:05Z",
    "title_canon_sha256": "b3befa5d3b4f460f582105c2f162c344beb9fd715bbd44b0996f1074b7ec1777"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.20066",
    "kind": "arxiv",
    "version": 2
  }
}