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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mercadier, Deniz Sayin, Stella, Federico, Bizeau, Aurel, Talabot, Nicolas, Fua, Pascal
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911727428304896
author Mercadier, Deniz Sayin
Stella, Federico
Bizeau, Aurel
Talabot, Nicolas
Fua, Pascal
author_facet Mercadier, Deniz Sayin
Stella, Federico
Bizeau, Aurel
Talabot, Nicolas
Fua, Pascal
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29761
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
Mercadier, Deniz Sayin
Stella, Federico
Bizeau, Aurel
Talabot, Nicolas
Fua, Pascal
Computer Vision and Pattern Recognition
Computational Geometry
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.
title S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
topic Computer Vision and Pattern Recognition
Computational Geometry
url https://arxiv.org/abs/2605.29761