5 papers
Point-Based 3D Reconstruction from Sparse Views under Known Illumination
Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad +3
Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods i…
Differentiable Voxelization of Surface Representations
Tobias Djuren, Ugo Finnendahl, Markus Worchel +2
Different shape representations facilitate different computations. Surface representations, in particular meshes, are often used for modeling, whereas volume representations are us…
As-Rigid-As-Possible Regularization for Implicit Surfaces
Tobias Djuren, Markus Worchel, Ugo Finnendahl +1
Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularization, penalizing the deviation o…
Radiative Backpropagation with Non-Static Geometry
Markus Worchel, Ugo Finnendahl, Marc Alexa
Radiative backpropagation-based (RB) methods efficiently compute reverse-mode derivatives in physically-based differentiable rendering by simulating the propagation of differential…
Differentiable Shadow Mapping for Efficient Inverse Graphics
Markus Worchel, Marc Alexa
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 approx…