Pith Number

pith:7MNTUTZT

pith:2026:7MNTUTZTD6NNQFL2JOAWWBFYXE

not attested not anchored not stored refs resolved

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction

Chris Broaddus, Laurent Guigues, Siyu Huang, Weiwei Sun, Xi Liu, Zhou Ren

HAD estimates pixel-wise hallucination scores from a pre-trained novel view synthesis network to mask unreliable pixels in diffusion-augmented images during sparse-view 3D reconstruction.

arxiv:2605.16873 v1 · 2026-05-16 · 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{7MNTUTZTD6NNQFL2JOAWWBFYXE}

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

HAD estimates pixel-wise hallucination score maps for augmented images by leveraging multi-view reasoning capabilities from a feedforward novel view synthesis (NVS) network pre-trained on large-scale 3D data, enabling selective masking of unreliable pixels during progressive 3D reconstruction and achieving state-of-the-art performance across multiple benchmarks on novel view synthesis.

C2weakest assumption

The pre-trained feedforward NVS network can reliably produce hallucination scores that accurately identify pixels inconsistent with the original input views, and that masking these pixels improves rather than harms the final 3D model quality.

C3one line summary

HAD uses multi-view reasoning from a pre-trained feedforward NVS network to estimate and mask hallucination scores in diffusion priors, reducing artifacts and achieving SOTA novel view synthesis in sparse-view 3D reconstruction.

References

57 extracted · 57 resolved · 4 Pith anchors

[1] Instant uncertainty calibration of nerfs us- ing a meta-calibrator 2024

[2] Mip-nerf: A multiscale representation for anti-aliasing neu- ral radiance fields

[3] Mip-nerf 360: Unbounded anti-aliased neural radiance fields 2022

[4] Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets 2023 · arXiv:2311.15127

[5] Tensorf: Tensorial radiance fields 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:27.564453Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fb1b3a4f331f9ad8157a4b816b04b8b91cbf6d9fe8168ac842c4af5a9b769b80

Aliases

arxiv: 2605.16873 · arxiv_version: 2605.16873v1 · doi: 10.48550/arxiv.2605.16873 · pith_short_12: 7MNTUTZTD6NN · pith_short_16: 7MNTUTZTD6NNQFL2 · pith_short_8: 7MNTUTZT

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/7MNTUTZTD6NNQFL2JOAWWBFYXE \
  | 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: fb1b3a4f331f9ad8157a4b816b04b8b91cbf6d9fe8168ac842c4af5a9b769b80

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e22c607ca7eca0b598ea17dca82d961f4c1e19cbe3eedb0c8e551a14b7cb112d",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T08:31:39Z",
    "title_canon_sha256": "0d55bef7bb8f447cfedefdc654ec3678e300c007c59814e933b08f3e1f70236a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16873",
    "kind": "arxiv",
    "version": 1
  }
}