arXiv subjects

Markus Worchel

Publications and source records attributed to Markus Worchel.

7 recordsLinked to original sources

arXiv2026

Point-Based 3D Reconstruction from Sparse Views under Known Illumination

Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods improve extracted geometry through oriented primitives and regularization, while RadiosityGS incorporates differentiable light transport through a radiosity inspired finite-element surfel formulation. We propose a differentiable point rendering method based on opacity-bearing beta surfels. An opacity explicit adjoint light transport formulation provides gradients for surfel geometry and appearance parameters, allowing physically based light transport to constrain reconstruction. Across five synthetic objects reconstructed from ten posed views, our method achieves the lowest mean symmetric Chamfer distance among the evaluated baselines and reduces mean Chamfer distance by 28.5% relative to the strongest point-based baseline while using only 267 surfels on average, approximately ~161 fewer primitives. Directional Chamfer results further show improved accuracy and competitive completion relative to related point-based methods. These results show that, in the controlled direct illumination setting, compact beta surfels combined with transport-based optimization can recover surfaces without relying on the tens to hundreds of thousands of primitives used by the evaluated baselines.

cs.CV↗

arXiv2026

As-Rigid-As-Possible Regularization for Implicit Surfaces

Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularization, penalizing the deviation of the surface from its original shape. The popular as-rigid-aspossible (ARAP) energy strikes a good compromise between realistic deformation behavior and efficient computation, at least for piecewise linear meshes. We develop an approach for computing the ARAP energy of a deformation function based on point sampling of the surface. The implicit representation is exploited to provide differentials in each sample. The evaluation is efficient and exact in each sample (up to numerical precision). We demonstrate the general applicability of the method to neural shape processing in several applications and contrast its properties with alternatives from the literature.

cs.GR↗

arXiv2026

Differentiable Voxelization of Surface Representations

Different shape representations facilitate different computations. Surface representations, in particular meshes, are often used for modeling, whereas volume representations are useful for spatial queries such as intersection or containment. Optimizing a surface representation based on a volumetric properties by gradient descent requires the derivatives of the volume relative to its bounding surface. We derive this gradient for winding numbers and show that it can be efficiently computed for volumetric values sampled on a regular grid (voxel representation) and surface parameters based on vertex sets (triangle meshes). This enables an efficient solution for a variety of optimization problems. We demonstrate the practical use of this approach at the examples of deforming meshes to resolve intersections, being manufacturable by cutting with a bandsaw from three directions, and creating shapes that are close to tiling 3D space.

cs.GR↗

arXiv2025

Radiative Backpropagation with Non-Static Geometry

Radiative backpropagation-based (RB) methods efficiently compute reverse-mode derivatives in physically-based differentiable rendering by simulating the propagation of differential radiance. A key assumption is that differential radiance is transported like normal radiance. We observe that this holds only when scene geometry is static and demonstrate that current implementations of radiative backpropagation produce biased gradients when scene parameters change geometry. In this work, we derive the differential transport equation without assuming static geometry. An immediate consequence is that the parameterization matters when the sampling process is not differentiated: only surface integrals allow a local formulation of the derivatives, i.e., one in which moving surfaces do not affect the entire path geometry. While considerable effort has been devoted to handling discontinuities resulting from moving geometry, we show that a biased interior derivative compromises even the simplest inverse rendering tasks, regardless of discontinuities. An implementation based on our derivation leads to systematic convergence to the reference solution in the same setting and provides unbiased RB interior derivatives for path-space differentiable rendering.

cs.GR↗

arXiv2023

Differentiable Shadow Mapping for Efficient Inverse Graphics

We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy -- while differentiable rasterization without shadows often fails to converge.

cs.GR↗

arXiv2022

Multi-View Mesh Reconstruction with Neural Deferred Shading

We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While flexible, neural surface representations are a significant bottleneck in optimization runtime. Instead, we represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rasterization and neural shading. The renderer is used in a gradient descent optimization where both a triangle mesh and a neural shader are jointly optimized to reproduce the multi-view images. We evaluate our method on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines and neural approaches while surpassing them in optimization runtime. Additionally, we investigate the shader and find that it learns an interpretable representation of appearance, enabling applications such as 3D material editing.

cs.CV↗

arXiv2022

Accurate Human Body Reconstruction for Volumetric Video

In this work, we enhance a professional end-to-end volumetric video production pipeline to achieve high-fidelity human body reconstruction using only passive cameras. While current volumetric video approaches estimate depth maps using traditional stereo matching techniques, we introduce and optimize deep learning-based multi-view stereo networks for depth map estimation in the context of professional volumetric video reconstruction. Furthermore, we propose a novel depth map post-processing approach including filtering and fusion, by taking into account photometric confidence, cross-view geometric consistency, foreground masks as well as camera viewing frustums. We show that our method can generate high levels of geometric detail for reconstructed human bodies.

cs.CV↗