Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction
This addresses a domain-specific challenge in 3D modeling for applications like autonomous driving and gaming, offering incremental improvements to handle reflective and transparent materials.
The paper tackles the problem of inaccurate 3D car reconstruction due to reflective and transparent surfaces by proposing Car-GS, which introduces view-dependent Gaussian primitives, geometry-specific opacity, and a quality-aware supervision module, achieving precise reconstruction and outperforming prior methods.
3D car modeling is crucial for applications in autonomous driving systems, virtual and augmented reality, and gaming. However, due to the distinctive properties of cars, such as highly reflective and transparent surface materials, existing methods often struggle to achieve accurate 3D car reconstruction.To address these limitations, we propose Car-GS, a novel approach designed to mitigate the effects of specular highlights and the coupling of RGB and geometry in 3D geometric and shading reconstruction (3DGS). Our method incorporates three key innovations: First, we introduce view-dependent Gaussian primitives to effectively model surface reflections. Second, we identify the limitations of using a shared opacity parameter for both image rendering and geometric attributes when modeling transparent objects. To overcome this, we assign a learnable geometry-specific opacity to each 2D Gaussian primitive, dedicated solely to rendering depth and normals. Third, we observe that reconstruction errors are most prominent when the camera view is nearly orthogonal to glass surfaces. To address this issue, we develop a quality-aware supervision module that adaptively leverages normal priors from a pre-trained large-scale normal model.Experimental results demonstrate that Car-GS achieves precise reconstruction of car surfaces and significantly outperforms prior methods. The project page is available at https://lcc815.github.io/Car-GS.