$α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
This addresses a specific challenge in computer vision for applications like 3D scanning and virtual reality, but it is incremental as it builds on prior implicit surface and NeRF techniques.
The paper tackles the problem of reconstructing surfaces for semi-transparent and thin objects, which existing methods like SDF and NeRF struggle with due to assumptions of solid surfaces or coupled geometry and opacity. It presents αSurf, a novel representation that decouples geometry and opacity, achieving better reconstruction quality with fewer artifacts than state-of-the-art methods.
Implicit surface representations such as the signed distance function (SDF) have emerged as a promising approach for image-based surface reconstruction. However, existing optimization methods assume solid surfaces and are therefore unable to properly reconstruct semi-transparent surfaces and thin structures, which also exhibit low opacity due to the blending effect with the background. While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts. We present $α$Surf, a novel surface representation with decoupled geometry and opacity for the reconstruction of semi-transparent and thin surfaces where the colors mix. Ray-surface intersections on our representation can be found in closed-form via analytical solutions of cubic polynomials, avoiding Monte-Carlo sampling and is fully differentiable by construction. Our qualitative and quantitative evaluations show that our approach can accurately reconstruct surfaces with semi-transparent and thin parts with fewer artifacts, achieving better reconstruction quality than state-of-the-art SDF and NeRF methods. Website: https://alphasurf.netlify.app/