Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields

About

Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limitation of this approach is that multiple SDFs can produce geometries that interpenetrate, violating physical plausibility. Existing mitigation strategies rely on soft penalty terms that reduce but do not eliminate intersections, and require careful loss weighting. To truly prevent interpenetration, we propose a hard constraint on vector-valued SDFs and introduce S2MDF, a lightweight plug-and-play module that enforces the constraint on any object-compositional SDF representation without architectural modifications. It introduces negligible computational overhead and is compatible with linearly-interpolated standard meshing algorithms such as Marching Cubes. It can be applied during training or as a post-processing step. Experiments on multiple state-of-the-art compositional methods show that S2MDF reduces intersections to numerical precision while preserving reconstruction quality, outperforming existing mitigation strategies.

Deniz Sayin Mercadier, Federico Stella, Aurel Bizeau, Nicolas Talabot, Pascal Fua• 2026

Related benchmarks

TaskDatasetResultRank
3D organ reconstructionTS-Lung Both v1 (test)
MCD5.357
5
3D organ reconstructionMMWHS Heart v1 (test)
MCD (Mean Contour Distance)23.094
5
Object-compositional 3D scene reconstructionReplica 8 scenes
MCD1.847
5
Shape ReconstructionPartNet Chairs (test)
MCD2.173
5
Shape ReconstructionMixers (test)
MCD1.161
5
Showing 5 of 5 rows

Other info

Follow for update