GRApr 26

Distance Field Rasterization for End-to-End Mesh Reconstruction

arXiv:2604.2353774.5
Predicted impact top 24% in GR · last 90 daysOriginality Incremental advance
AI Analysis

Provides a novel method for real-time, high-quality 3D reconstruction without post-processing, benefiting computer vision and graphics applications.

SDFRaster combines rasterization efficiency with signed distance fields for end-to-end mesh reconstruction, achieving higher-quality and more complete surfaces with lower storage cost than state-of-the-art on DTU and Tanks and Temples.

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/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes