pith. sign in
Pith Number

pith:W7EVYY73

pith:2025:W7EVYY73AJQPRBOQGAB6K7EDNE
not attested not anchored not stored refs resolved

TTT3R: 3D Reconstruction as Test-Time Training

Andreas Geiger, Anpei Chen, Xingyu Chen, Yue Chen, Yuliang Xiu

Framing 3D reconstruction as test-time training yields a closed-form learning rate from alignment confidence that doubles global pose accuracy on long sequences.

arxiv:2509.26645 v4 · 2025-09-30 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{W7EVYY73AJQPRBOQGAB6K7EDNE}

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

This training-free intervention, termed TTT3R, substantially improves length generalization, achieving a 2× improvement in global pose estimation over baselines, while operating at 20 FPS with just 6 GB of GPU memory to process thousands of images.

C2weakest assumption

That alignment confidence between the memory state and incoming observations can be computed reliably and directly yields a closed-form learning rate that correctly balances retention of history with adaptation to new data without introducing instability or bias.

C3one line summary

TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.

References

112 extracted · 112 resolved · 18 Pith anchors

[1] Bundle adjustment in the large 2010
[2] Building rome in a day.ACM Communications, 2011 2011
[3] Cross-view completion models are zero-shot correspondence estimators 2024
[4] Speeded-up robust features (surf).Computer vision and image understanding, 2008 2008
[5] xlstm: Extended long short-term memory 2024

Formal links

1 machine-checked theorem link

Cited by

19 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:14.802949Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b7c95c63fb0260f885d03003e57c83690a56bdacde9bc816fbfbd059b4ca1e07

Aliases

arxiv: 2509.26645 · arxiv_version: 2509.26645v4 · doi: 10.48550/arxiv.2509.26645 · pith_short_12: W7EVYY73AJQP · pith_short_16: W7EVYY73AJQPRBOQ · pith_short_8: W7EVYY73
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/W7EVYY73AJQPRBOQGAB6K7EDNE \
  | 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: b7c95c63fb0260f885d03003e57c83690a56bdacde9bc816fbfbd059b4ca1e07
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "faf78cda85d0821e0ca3b7bc112f727b3a7f0ffb3ce8164936548f6b91e0d2d5",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-09-30T17:59:51Z",
    "title_canon_sha256": "a769ed00c8dcbbcee71e9d931c89007e9966939155db4db9d109d16b780217c0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.26645",
    "kind": "arxiv",
    "version": 4
  }
}