Abstract
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, reducing mean Chamfer distance by 28.5% relative to the strongest 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.
Across five synthetic objects reconstructed from ten posed views, our method achieves the lowest mean symmetric Chamfer distance among the evaluated baselines, reducing mean Chamfer distance by 28.5% relative to the strongest 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.
| Original language | English |
|---|---|
| Title of host publication | Point-Based 3D Reconstruction from Sparse Views under Known Illumination |
| Number of pages | 14 |
| Publication status | Accepted/In press - 6 Aug 2026 |
Fingerprint
Dive into the research topics of 'Point-Based 3D Reconstruction from Sparse Views under Known Illumination'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver