AI Paper Atlas

Research map / 3D vision / Face and shape

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Sanghyun Son, Matheus Gadelha, Yang Zhou, Matthew Fisher, Zexiang Xu, Yi-Ling Qiao, Ming C. Lin, Yi Zhou

ICCV 2025 · 3D vision › Face and shape · approach: Optimization-based shape matching · 10 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
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 2D font reconstructiontime (sec): 30.39 -> 11.33Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 2D font reconstructionChamfer Distance (x1e-6): 1.97 -> 1.82Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 3D point cloud reconstruction (50 models, oriented)Chamfer Distance (x1e-3): 0.154 -> 0.033Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 3D point cloud reconstruction (50 models, oriented)time (sec): 1147 -> 282Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 3D multi-view reconstructionChamfer Distance (x1e-3): 0.697 -> 0.342Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 3D multi-view reconstructiontime (sec): 772 -> 205Improved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · 3D tessellation face probability computationspeed: up to 16 times faster in 2D and 32 times faster in 3DImproved
replace DMesh's weighted Delaunay tessellation with the Minimum-Ball conditionDMesh · tessellation GPU memoryGPU memory: up to 96% less in 2D and 75% less in 3DImproved
use oriented instead of unoriented point clouds as inputDMesh++ · 3D point cloud reconstruction (50 models)Chamfer Distance (x1e-3): 0.034 -> 0.033No clear effect
use DMesh++ instead of PSR/VoroMesh/PoNQ on open-surface modelspoint cloud reconstruction · 3D point cloud reconstruction (500 Thingi10K models, open surfaces)Chamfer Distance (x1e-4): 7.86 -> 0.37Improved
use DMesh++ instead of PoNQ on closed-surface modelspoint cloud reconstruction · 3D point cloud reconstruction (500 Thingi10K models, closed surfaces)Chamfer Distance (x1e-4): 2.44 -> 0.37Improved
use DMesh++ instead of oriented-input DMesh on F1 and runtime tradeoff versus PSRpoint cloud reconstruction · 3D point cloud reconstruction (50 models, oriented)time (sec): 4 -> 282Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 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