Pith Number

pith:6AH3ZZDN

pith:2026:6AH3ZZDN3ABQY5RSIRAXDWTVHD

not attested not anchored not stored refs resolved

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

Honggyu An, Jaewoo Jung, Jahyeok Koo, Jisu Nam, Junhwa Hur, Seungryong Kim, Soowon Son

A video diffusion transformer can be repurposed as a feed-forward dense 3D tracker that follows every pixel from a reference frame across a monocular video.

arxiv:2605.12587 v1 · 2026-05-12 · 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{6AH3ZZDN3ABQY5RSIRAXDWTVHD}

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

We present TrackCraft3R, the first method to repurpose a video DiT as a feed-forward dense 3D tracker... achieves state-of-the-art performance on standard sparse and dense 3D tracking benchmarks, while running 1.3x faster and using 4.6x less peak memory than the strongest prior method.

C2weakest assumption

That the frame-anchored generative priors in pre-trained video DiTs can be converted into reliable reference-anchored dense 3D tracking through a dual-latent representation and temporal RoPE alignment with only LoRA fine-tuning.

C3one line summary

TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.

References

87 extracted · 87 resolved · 12 Pith anchors

[1] Mapillary planet-scale depth dataset 2020

[2] Track2Act: Predicting point tracks from internet videos enables generalizable robot manipulation 2024

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

[4] Virtual KITTI 2 2001 · arXiv:2001.10773

[5] Videojam: Joint appearance-motion representations for en- hanced motion generation in video models 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:10:01.325294Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f00fbce46dd8030c7632444171da7538c2a8f5fd9bb22ff3bffbbbf2f4cf04bb

Aliases

arxiv: 2605.12587 · arxiv_version: 2605.12587v1 · doi: 10.48550/arxiv.2605.12587 · pith_short_12: 6AH3ZZDN3ABQ · pith_short_16: 6AH3ZZDN3ABQY5RS · pith_short_8: 6AH3ZZDN

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/6AH3ZZDN3ABQY5RSIRAXDWTVHD \
  | 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: f00fbce46dd8030c7632444171da7538c2a8f5fd9bb22ff3bffbbbf2f4cf04bb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "abb9dd44c37e5fa9675b30ceae4bd8cfa4f54c25358f0789f382cfb9d5e0f9a1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T17:59:27Z",
    "title_canon_sha256": "92e950ff5237697de1a3af334e358ee728d64257b9df21e071503270a82c0e20"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12587",
    "kind": "arxiv",
    "version": 1
  }
}