AI Paper Atlas

Research map / 3D vision / Face and shape

DeepMesh: Differentiable Iso-Surface Extraction

Benoît Guillard, Edoardo Remelli, Artem Lukoianov, Pierre Yvernay, Stephan R. Richter, Timur Bagautdinov, Pierre Baqué, Pascal Fua

TPAMI 2024 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 27 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 contour-matching refinement through differentiable mesh (ablation)DeepMesh SDF · ShapeNet car SVRChamfer distance x1e4: 2.96 -> 2.56Improved
add contour-matching refinement through differentiable mesh (ablation)DeepMesh SDF · ShapeNet chair SVRChamfer distance x1e4: 9.07 -> 8.22Improved
add differentiable-rendering silhouette refinement (ablation)DeepMesh SDF · ShapeNet car SVRChamfer distance x1e4: 2.96 -> 2.73Improved
use SDF instead of occupancy field (ablation)DeepMesh refinement · ShapeNet chair SVRChamfer distance x1e4: 10.35 -> 8.22Improved
add refinement through differentiable mesh (ablation)DeepMesh occupancy · ShapeNet car SVRChamfer distance x1e4: 3.02 -> 2.65Improved
add refinement on real images (ablation)DeepMesh (raw) · Pix3D ChairsChamfer distance x1e3: 4.850 -> 4.063Improved
use learned DeepMesh parameterization instead of hand-crafted FreeFormFreeForm · CFD drag minimizationrelative drag objective: 0.844 -> 0.675Improved
use SDF instead of occupancy network (ablation)DeepMesh · CFD drag minimizationrelative drag objective: 0.721 -> 0.675Improved
add mesh-based refinement of latent features (ablation)ConvOccNet · Scene reconstructionChamfer distance: 0.954 -> 0.529Improved
add mesh-based refinement of latent features (ablation)ConvOccNet · Scene reconstructionIoU %: 81.67 % -> 88.74 %Improved
add Chamfer loss to implicit loss in training (ablation)DeepSDF · ShapeNet LampsChamfer distance x1e4: 8.12 -> 7.59Improved
add Chamfer loss to implicit loss in training (ablation)DeepSDF · ShapeNet ChairsChamfer distance x1e4: 2.75 -> 2.56Improved

Later papers that compared with this method

4 later accepted papers report DeepMesh as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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