Distance Field Rasterization for End-to-End Mesh Reconstruction

TL;DR

SDFRaster is a novel method combining rasterization and signed distance fields for efficient, end-to-end mesh reconstruction without post-processing, outperforming existing approaches in quality and storage.

Contribution

It introduces a rasterizable SDF representation optimized over a tetrahedral grid, enabling direct, differentiable mesh extraction in an end-to-end manner.

Findings

Achieves higher-quality surface reconstructions than state-of-the-art methods.

Reduces storage costs compared to existing approaches.

Enables end-to-end mesh reconstruction without post-processing.

Abstract

Rasterization based methods have recently enabled high-quality novel view synthesis at real-time rates, but their underlying volumetric primitives do not expose a direct, globally consistent surface representation, leaving sur face extraction to heuristic post-processing. In contrast, implicit signed dis tance field (SDF) methods provide well-defined surfaces but are typically optimized with computationally expensive ray marching. We propose SD FRaster, a rasterizable SDF representation that bridges this gap by combin ing the efficiency of rasterization with signed distance field for end-to-end mesh reconstruction. Starting from a Delaunay tetrahedralization, we op timize a continuous SDF over a tetrahedral grid and render it efficiently by rasterizing tetrahedra and alpha-compositing their contributions. We further integrate differentiable Marching Tetrahedra into the optimization loop, enablingend-to-endmeshreconstructionwithoutpost-processingmesh extraction. Experiments on DTU and Tanks and Temples demonstrate that SDFRaster achieves higher-quality and more complete surface reconstruc tions with lower storage cost than state-of-the-art approaches. Project page: https://ustc3dv.github.io/SDFRaster/