Pith Number

pith:LRH4IMVR

pith:2024:LRH4IMVRKXHH5WK7R6JI4JQAAY

not attested not anchored not stored refs resolved

3D Reconstruction with Spatial Memory

Hengyi Wang, Lourdes Agapito

Spann3R maintains an external spatial memory to regress per-image pointmaps directly in a global coordinate system from ordered or unordered image collections.

arxiv:2408.16061 v1 · 2024-08-28 · 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{LRH4IMVRKXHH5WK7R6JI4JQAAY}

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

Spann3R can predict per-image pointmaps expressed in a global coordinate system, thus eliminating the need for optimization-based global alignment.

C2weakest assumption

That an external spatial memory can reliably retain and retrieve all relevant prior 3D information across arbitrary ordered or unordered image collections without drift or loss of consistency.

C3one line summary

Spann3R uses a learned spatial memory to regress per-image pointmaps directly in a shared global coordinate system, removing the need for optimization-based alignment after per-pair predictions.

References

95 extracted · 95 resolved · 1 Pith anchors

[1] Large-scale data for multiple-view stereopsis 2016

[2] Building rome in a day 2009

[3] Bundle adjustment in the large 2010

[4] Map-free visual relocalization: Metric pose relative to a single image 2022

[5] Human mem- ory: A proposed system and its control processes

Formal links

3 machine-checked theorem links

Cited by

27 papers in Pith

Geo-Align: Video Generation Alignment via Metric Geometry Reward

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model

Receipt and verification

First computed	2026-05-17T23:38:14.710171Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5c4fc432b155ce7ed95f8f928e2600060c3c5ae7125af5c2bf693c918c2944c9

Aliases

arxiv: 2408.16061 · arxiv_version: 2408.16061v1 · doi: 10.48550/arxiv.2408.16061 · pith_short_12: LRH4IMVRKXHH · pith_short_16: LRH4IMVRKXHH5WK7 · pith_short_8: LRH4IMVR

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/LRH4IMVRKXHH5WK7R6JI4JQAAY \
  | 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: 5c4fc432b155ce7ed95f8f928e2600060c3c5ae7125af5c2bf693c918c2944c9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "711a85e5d4b0a857caa58f1b88e7ed5577c5774cdf899299a3dfd5ccd25c0aa4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-08-28T18:01:00Z",
    "title_canon_sha256": "17982137ab62ade0bdda625fa03bdd957a111e965c8102f4d6701d90112f25f8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.16061",
    "kind": "arxiv",
    "version": 1
  }
}