Papers › DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

29 Feb 2024CVPR 2024 1arXiv:2402.19302archive 2025-07-28

Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari, Pietro Morerio, Alessio Del Bue

Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context, we posit that a general unified model can effectively address them all, irrespective of the input data type (images, 3D, etc.). We introduce DiffAssemble, a Graph Neural Network (GNN)-based architecture that learns to solve reassembly tasks using a diffusion model formulation. Our method treats the elements of a set, whether pieces of 2D patch or 3D object fragments, as nodes of a spatial graph. Training is performed by introducing noise into the position and rotation of the elements and iteratively denoising them to reconstruct the coherent initial pose. DiffAssemble achieves state-of-the-art (SOTA) results in most 2D and 3D reassembly tasks and is the first learning-based approach that solves 2D puzzles for both rotation and translation. Furthermore, we highlight its remarkable reduction in run-time, performing 11 times faster than the quickest optimization-based method for puzzle solving. Code available at https://github.com/IIT-PAVIS/DiffAssemble

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.19302")

Code

Syntology Ran 8 of 16 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

iit-pavis/diffassemble officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 8 ran; 3 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
3ran
8unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from iit-pavis/diffassemble. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Exophormer_GNN iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran no licence file found · pointer only · c6ba46a75cc4c7de · report
GCN iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran no licence file found · pointer only · 853fb3e8375b1a22 · report
Transformer_GNN iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran no licence file found · pointer only · ee30ebfbd2d26e63 · report
cosine_beta_schedule iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 66961a32f6104980 · report
cosine_discrete_beta_schedule iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 75938900df057f17 · report
interpolate_color iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 65d377dcba896cef · report
interpolate_color1d iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 0758f1d8eda12e1f · report
linear_beta_schedule iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 37a36e71b86103ce · report
BasicBlock iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · c15dde48a426f277 · report
Eff_GAT iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · 8c0f25a0642ad0c9 · report
GNN_Diffusion iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · 07d8d928387b7cde · report
ModelScheduler iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · 08a34a30f6b7319f · report
ResNet iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · 563e4b5350a21f15 · report
ResNet18 iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · 6f3ee56844431d2a · report
extract iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · df91df5171beed9b · report
greedy_cost_assignment iit-pavis/diffassemble/puzzle_diff/model/spatial_diffusion.py official repository unverified no licence file found · pointer only · d726810ea6025a06 · report

Tasks

DenoisingGraph Neural Network

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionGraph Neural Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections