pith. sign in
Pith Number

pith:LE7WGICD

pith:2026:LE7WGICDUR7IKHGMZFIUYT6W5E
not attested not anchored not stored refs resolved

DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

Jie Guo, Nisha Huang, Tong-Yee Lee, Xiu Li, Yizhou Lin, Zitong Yu

DealMaTe transfers materials across objects using depth, normal, and lighting images in a text-free diffusion framework.

arxiv:2605.15681 v1 · 2026-05-15 · cs.GR · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LE7WGICDUR7IKHGMZFIUYT6W5E}

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

Extensive experiments covering a wide variety of objects and lighting conditions consistently demonstrate that DealMaTe achieves remarkable high-fidelity material transfer under arbitrary input materials.

C2weakest assumption

The lightweight 3D information injection method (Multi-Dim 3D Shader LoRA) enables compatible control conditions and achieves harmonious and stable results without modifying the base model weights.

C3one line summary

DealMaTe proposes a simplified diffusion framework for material transfer that injects multi-dimensional 3D conditions via Multi-Dim 3D Shader LoRA and Shader Causal Mutual Attention with KV caching.

References

71 extracted · 71 resolved · 2 Pith anchors

[1] Louis-Philippe Asselin, Denis Laurendeau, and Jean-Francois Lalonde. 2020. Deep SVBRDF estimation on real materials. InInternational Conference on 3D Vision (3DV). IEEE, 1157–1166 2020
[2] Tim Brooks, Aleksander Holynski, and Alexei A Efros. 2023. Instructpix2pix: Learning to follow image editing instructions. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog 2023
[3] George Cazenavette, Tongzhou Wang, Antonio Torralba, Alexei A Efros, and Jun-Yan Zhu. 2022. Wearable ImageNet: Synthesizing tileable textures via dataset distillation. InProceedings of the IEEE/CVF Co 2022
[4] Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee, Sergey Tulyakov, and Matthias Nießner. 2023. Text2tex: Text-driven texture synthesis via diffusion models. In Proceedings of the IEEE/CVF International 2023
[5] Junsong Chen, YU Jincheng, GE Chongjian, Lewei Yao, Enze Xie, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024. Pixart-𝛼: Fast training of diffusion transformer for photorealistic 2024
Receipt and verification
First computed 2026-05-20T00:01:12.089569Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

593f632043a47e851cccc9514c4fd6e930aa571d9f6525961cbb80247fcf51e2

Aliases

arxiv: 2605.15681 · arxiv_version: 2605.15681v1 · doi: 10.48550/arxiv.2605.15681 · pith_short_12: LE7WGICDUR7I · pith_short_16: LE7WGICDUR7IKHGM · pith_short_8: LE7WGICD
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LE7WGICDUR7IKHGMZFIUYT6W5E \
  | 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: 593f632043a47e851cccc9514c4fd6e930aa571d9f6525961cbb80247fcf51e2
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "393da71a8de242486d2f99a769b0270d4e726baf08e02c82a3c54018d3d9f9fe",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.GR",
    "submitted_at": "2026-05-15T07:06:39Z",
    "title_canon_sha256": "a5cbce7588074fcd5e23685409bbdb987c8e025332ec8d52a5ca21bf384dc318"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15681",
    "kind": "arxiv",
    "version": 1
  }
}