Year: 2025
Type: conference-paper
Abstract: Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a significant bottleneck for existing methods and hindering new applications. In response, we propose a pair of highly scalable components for 3D neural fields: Lightplane Renderer and Splatter, which significantly reduce memory usage in 2D-3D mapping (over$\mathbf{1 0 0 0} \times)$. These innovations enable the processing of vastly more and higher resolution images with significantly small memory and computational costs. We demonstrate their utility across various applications, from optimizing with image-level losses to enabling a versatile pipeline for scaling 3D reconstruction and generation.11work done during internship
Institutions: Meta (United States), University of Michigan
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4413513748