Papers › MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization

MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization

5 Aug 2024arXiv:2408.02555archive 2025-07-28

YiWen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang, Zilong Chen, Jun Zhu, Chi Zhang, Guosheng Lin

Meshes are the de facto 3D representation in the industry but are labor-intensive to produce. Recently, a line of research has focused on autoregressively generating meshes. This approach processes meshes into a sequence composed of vertices and then generates them vertex by vertex, similar to how a language model generates text. These methods have achieved some success but still struggle to generate complex meshes. One primary reason for this limitation is their inefficient tokenization methods. To address this issue, we introduce MeshAnything V2, an advanced mesh generation model designed to create Artist-Created Meshes that align precisely with specified shapes. A key innovation behind MeshAnything V2 is our novel Adjacent Mesh Tokenization (AMT) method. Unlike traditional approaches that represent each face using three vertices, AMT optimizes this by employing a single vertex wherever feasible, effectively reducing the token sequence length by about half on average. This not only streamlines the tokenization process but also results in more compact and well-structured sequences, enhancing the efficiency of mesh generation. With these improvements, MeshAnything V2 effectively doubles the face limit compared to previous models, delivering superior performance without increasing computational costs. We will make our code and models publicly available. Project Page: https://buaacyw.github.io/meshanything-v2/

PaperPDFCodeCode 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="2408.02555")

Code

Syntology Ran 14 of 15 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 14 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

buaacyw/meshanythingv2 officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

15 samples harvested; 14 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

14ran
1unverified

Licence: 15 of the 15 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 buaacyw/meshanythingv2. “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.

adjacent_mesh_tokenization buaacyw/meshanythingv2/adjacent_mesh_tokenization.py official repository ran licence not identified · pointer only · e9606ff84628c6ef · report
adjust_learning_rate buaacyw/meshanythingv2/meshanything_train/engine.py official repository ran licence not identified · pointer only · f4eafced0f46835f · report
all_reduce_average buaacyw/meshanythingv2/meshanything_train/dist.py official repository ran licence not identified · pointer only · 9a23b811ac255883 · report
all_reduce_sum buaacyw/meshanythingv2/meshanything_train/dist.py official repository ran licence not identified · pointer only · 0a44bac5b9e928b3 · report
calc_chamfer_loss buaacyw/meshanythingv2/meshanything_train/eval_cond_gpt.py official repository ran fingerprinted licence not identified · pointer only · aa8368e02831cd41 · report
compute_learning_rate buaacyw/meshanythingv2/meshanything_train/engine.py official repository ran licence not identified · pointer only · 289df3d353cb834e · report
coor_discretize buaacyw/meshanythingv2/meshanything_train/models/single_gpt.py official repository ran licence not identified · pointer only · c7b9b68e57eaf4f1 · report
huber_loss buaacyw/meshanythingv2/meshanything_train/misc.py official repository ran fingerprinted licence not identified · pointer only · 03c93e1bacbbbf89 · report
reduce_dict buaacyw/meshanythingv2/meshanything_train/dist.py official repository ran licence not identified · pointer only · b420987753130180 · report
rotate_mesh buaacyw/meshanythingv2/meshanything_train/loop_set_256.py official repository ran fingerprinted licence not identified · pointer only · 674f1a100a19cda3 · report
to_list_1d buaacyw/meshanythingv2/meshanything_train/misc.py official repository ran licence not identified · pointer only · 62d58117b5f11382 · report
to_list_3d buaacyw/meshanythingv2/meshanything_train/misc.py official repository ran licence not identified · pointer only · d1ff61f9f8407220 · report
undiscretize buaacyw/meshanythingv2/MeshAnything/models/meshanything_v2.py official repository ran licence not identified · pointer only · 79746499645d28e7 · report
undiscretize buaacyw/meshanythingv2/meshanything_train/models/single_gpt.py official repository ran licence not identified · pointer only · 25573407df4ccb86 · report
normalize_vertices buaacyw/meshanythingv2/mesh_to_pc.py official repository unverified licence not identified · pointer only · 97498e437a3af57c · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAM

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