Pith Number

pith:PWNJNT6F

pith:2026:PWNJNT6FFXOM6YEMU55X4WMMOH

not attested not anchored not stored refs resolved

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Bo Yang, Jiahao Chen, Jinxi Li, Shenxing Wei, Yafei Yang, Zhixuan Sun, Zihui Zhang

EvObj adapts synthetic object priors to real 3D point clouds unsupervised by dynamically refining candidates and completing partial geometries.

arxiv:2605.13152 v1 · 2026-05-13 · cs.CV · cs.AI · cs.LG · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PWNJNT6FFXOM6YEMU55X4WMMOH}

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

EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.

C2weakest assumption

That the proposed object discerning and completion modules can reliably bridge the geometric domain gap between synthetic pretraining data and real-world point clouds (including morphological variations and occlusion artifacts) without any scene supervision or additional real-world labels.

C3one line summary

EvObj learns evolving object-centric representations for unsupervised 3D instance segmentation by dynamically refining object candidates and completing partial geometries to bridge the synthetic-to-real domain gap, outperforming baselines on real and synthetic datasets.

References

66 extracted · 66 resolved · 2 Pith anchors

[1] Joint 2d-3d-semantic data for indoor scene understanding 2017 · arXiv:1702.01105

[2] SLIM: Self-Supervised LiDAR Scene Flow and Motion Seg- mentation.ICCV, 2021 2021

[3] Open-YOLO 3D: Towards Fast and Accurate Open-V ocabulary 3D Instance Segmentation 2025

[4] Emerg- ing Properties in Self-Supervised Vision Transformers 2021

[5] ShapeNet: An Information-Rich 3D Model Repository 2015 · arXiv:1512.03012

Receipt and verification

First computed	2026-05-18T03:08:57.100635Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7d9a96cfc52ddccf608ca77b7e598c71f99ffde900c03a8ca9e6c212e2970352

Aliases

arxiv: 2605.13152 · arxiv_version: 2605.13152v1 · doi: 10.48550/arxiv.2605.13152 · pith_short_12: PWNJNT6FFXOM · pith_short_16: PWNJNT6FFXOM6YEM · pith_short_8: PWNJNT6F

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/PWNJNT6FFXOM6YEMU55X4WMMOH \
  | 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: 7d9a96cfc52ddccf608ca77b7e598c71f99ffde900c03a8ca9e6c212e2970352

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e4f4a7ad21a93e1a57c8a45cc04767b2c114d31b84d1ba346804e6a27cfaacb7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T08:17:45Z",
    "title_canon_sha256": "a6cdfe85a14cd8dc2533866ec7870bdcf28b75a6368665ccbb928104d497dfed"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13152",
    "kind": "arxiv",
    "version": 1
  }
}