Differentiable Neural Surface Refinement for Modeling Transparent Objects
Neural implicit surface reconstruction leveraging volume rendering has led to significant advances in multi-view reconstruction. However results for transparent objects can be very poor primarily because the rendering function fails to account for the intricate light transport induced by refraction and reflection. In this study we introduce transparent neural surface refinement (TNSR) a novel surface reconstruction framework that explicitly incorporates physical refraction and reflection tracing. Beginning with an initial approximate surface our method employs sphere tracing combined with Snell's law to cast both reflected and refracted rays. Central to our proposal is an innovative differentiable technique devised to allow signals from the photometric evidence to propagate back to the surface model by considering how the surface bends and reflects light rays. This allows us to connect surface refinement with volume rendering enabling end-to-end optimization solely on multi-view RGB images. In our experiments TNSR demonstrates significant improvements in novel view synthesis and geometry estimation of transparent objects without prior knowledge of the refractive index.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisSurface ReconstructionTransparent objectsSimilar Papers 제목 키워드 기반
DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objects
Reconstructing transparent objects from a set of multi-view images is a challenging task due to the complicated nature and indeterminate behavior of light propagation. Typical methods are primarily tailored to specific s…
RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives
Gaussian Splatting is a powerful tool for reconstructing diffuse scenes, but it struggles to simultaneously model specular reflections and the appearance of objects behind semi-transparent surfaces. These specular reflec…
Novel View SynthesisInteractive Visual Hull Refinement for Specular and Transparent Object Surface Reconstruction
In this paper we present a method of using standard multi-view images for 3D surface reconstruction of non-Lambertian objects. We extend the original visual hull concept to incorporate 3D cues presented by internal occlu…
Contour DetectionSurface ReconstructionTransparent objectsvalidTSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors
Reconstructing transparent surfaces is essential for tasks such as robotic manipulation in labs, yet it poses a significant challenge for 3D reconstruction techniques like 3D Gaussian Splatting (3DGS). These methods ofte…
3DGS3D ReconstructionDepth EstimationSurface Reconstruction+1$α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
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 ar…
NeRFSurface Reconstruction