Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer
This addresses geometric inconsistencies in in-the-wild novel view synthesis, offering an incremental improvement for applications like virtual reality and 3D reconstruction.
The paper tackled the problem of novel view synthesis from unstructured, in-the-wild image collections by introducing Geo-NVS-w, a geometry-aware framework that uses a Signed Distance Function (SDF) renderer and a Geometry-Preservation Loss, achieving competitive rendering performance with a 4-5x reduction in energy consumption compared to similar methods.
We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details.