Pith Number

pith:MULTON7L

pith:2024:MULTON7LSJF7UQ2C6SGB5KVG2C

not attested not anchored not stored refs resolved

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Brandon Smart, Chuanxia Zheng, Iro Laina, Victor Adrian Prisacariu

Splatt3R turns any uncalibrated stereo image pair into a 3D Gaussian splat without camera parameters or depth.

arxiv:2408.13912 v2 · 2024-08-25 · cs.CV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MULTON7LSJF7UQ2C6SGB5KVG2C}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without requiring any camera parameters or depth information... We train Splatt3R on the ScanNet++ dataset and demonstrate excellent generalisation to uncalibrated, in-the-wild images.

C2weakest assumption

That first optimizing only the 3D point cloud geometry loss and then switching to a novel view synthesis objective, combined with the proposed loss masking strategy, reliably avoids local minima that plague direct Gaussian splat training from stereo views.

C3one line summary

Splatt3R is a feed-forward network that predicts 3D Gaussian splats directly from uncalibrated stereo image pairs by extending MASt3R with appearance attributes and a two-stage training procedure.

References

69 extracted · 69 resolved · 0 Pith anchors

[1] The plenoptic func- tion and the elements of early vision 1991

[2] Computational stereo 1982

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

[4] Porf: Pose residual field for accurate neural sur- face reconstruction 2023

[5] Nope-nerf: Optimising neural ra- diance field with no pose prior 2023

Cited by

23 papers in Pith

The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates

Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks

MODEST: Multi-Optics Depth-of-Field Stereo Dataset

Receipt and verification

First computed	2026-05-17T23:38:46.006998Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

65173737eb924bfa4342f48c1eaaa6d0879d83747c551af85354ca098416db99

Aliases

arxiv: 2408.13912 · arxiv_version: 2408.13912v2 · doi: 10.48550/arxiv.2408.13912 · pith_short_12: MULTON7LSJF7 · pith_short_16: MULTON7LSJF7UQ2C · pith_short_8: MULTON7L

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/MULTON7LSJF7UQ2C6SGB5KVG2C \
  | 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: 65173737eb924bfa4342f48c1eaaa6d0879d83747c551af85354ca098416db99

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b3768bb736e07c4a570b15ed0a1454e7bcd611799b4b23ab0d040f7c0102c20f",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-08-25T18:27:20Z",
    "title_canon_sha256": "a1eb89593ad13f9b14c836cfd4e9a5aad90098d153ea00dc22e4c71b2171f402"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.13912",
    "kind": "arxiv",
    "version": 2
  }
}