Pith Number

pith:ZG63N5RU

pith:2024:ZG63N5RUVFBT4IQ76L7HSZM232

not attested not anchored not stored refs resolved

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Charles Herrmann, Deqing Sun, Forrester Cole, Junhwa Hur, Junyi Zhang, Ming-Hsuan Yang, Trevor Darrell, Varun Jampani

A pointmap estimator fine-tuned on limited dynamic video data can estimate geometry in moving scenes without explicit motion modeling.

arxiv:2410.03825 v2 · 2024-10-04 · 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{ZG63N5RUVFBT4IQ76L7HSZM232}

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

By posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics, even without an explicit motion representation.

C2weakest assumption

Suitable dynamic posed videos with depth labels exist in sufficient quantity and quality to allow fine-tuning to generalize to arbitrary motion and deformation.

C3one line summary

By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.

References

169 extracted · 169 resolved · 3 Pith anchors

[1] Scaling Learning Algorithms Towards

[2] and Osindero, Simon and Teh, Yee Whye , journal =

[3] Deep learning , author=. 2016 , publisher= 2016

[4] Repurposing diffusion-based image generators for monocular depth estimation , author=

[5] Wang, Wenshan and Hu, Yaoyu and Scherer, Sebastian , booktitle=CoRL, pages=. Tartan

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

Geo-Align: Video Generation Alignment via Metric Geometry Reward

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Receipt and verification

First computed	2026-05-17T23:38:52.330843Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c9bdb6f634a9433e221ff2fe79659ade9ead405d984801be53420d1c22b86162

Aliases

arxiv: 2410.03825 · arxiv_version: 2410.03825v2 · doi: 10.48550/arxiv.2410.03825 · pith_short_12: ZG63N5RUVFBT · pith_short_16: ZG63N5RUVFBT4IQ7 · pith_short_8: ZG63N5RU

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/ZG63N5RUVFBT4IQ76L7HSZM232 \
  | 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: c9bdb6f634a9433e221ff2fe79659ade9ead405d984801be53420d1c22b86162

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4ef1e44f308a1b30347c8c2ea073e4cbf7097eba2088aef40cf926fee55d7b04",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-10-04T18:00:07Z",
    "title_canon_sha256": "e10ca177b04eace8e788f2d234d9e873feb9c044caa4273ffd3087e0f4ca24ad"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.03825",
    "kind": "arxiv",
    "version": 2
  }
}