AI Paper Atlas

Research map / 3D vision / Face and shape

LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents

Tianhao Zhao, Youjia Zhang, Hang Long, Jinshen Zhang, Wenbing Li, Yang Yang, Gongbo Zhang, Jozef Hladký, Matthias Nießner, Wei Yang

ICML 2026 · 3D vision › Face and shape · approach: Textured mesh generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add VDF displacement field to VAE input (ablation)LATO VAE · VAE input ablationHD: 0.092 -> 0.075Improved
add VDF displacement field to VAE input (ablation)LATO VAE · VAE input ablationCD(L2): 0.043 -> 0.039Improved
add normal vectors to VAE input (ablation)LATO VAE · VAE input ablation|NC|: 0.832 -> 0.837Improved
add normal vectors to VAE input (ablation)LATO VAE · VAE input ablationHD: 0.076 -> 0.075Improved
increase sampled surface points from 81,920 to 819,200 (ablation)LATO VAE · VAE input ablationHD: 0.078 -> 0.075Improved
normalize each displacement vector (ablation)LATO VAE · VAE input ablationCD(L2): 0.039 -> 0.042Hurt
normalize displacement only above threshold tau (ablation)LATO VAE · VAE input ablationCD(L2): 0.039 -> 0.041Hurt
use VDF instead of discrete voxel labels as VAE input (ablation)LATO · VDF vs labeled voxelsqualitative structureImproved
add T-Voxel cross-attention in decoder (ablation)LATO decoder · T-Voxel cross-attention ablationqualitative meshImproved
replace geometric connectivity algorithm with learnable Connection Head (ablation)LATO · connectivity inferencegenerated sample qualityImproved
use continuous voxel VAE instead of per-face discrete tokensLATO vs MeshGPT · VAE reconstruction (artistic meshes)CD(L2): 0.050 -> 0.040Improved
use flow matching on T-Voxels instead of autoregressive generationLATO vs DeepMesh · Geometry-conditioned generation (dense meshes)CD(L2): 0.051 -> 0.043Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy