Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer

TL;DR

Geo-NVS-w is a geometry-aware novel view synthesis framework that uses an SDF-based representation and a new loss to produce photorealistic, geometrically consistent images from unstructured in-the-wild collections, with reduced energy consumption.

Contribution

It introduces a geometry-aware approach with an SDF renderer and a novel loss for preserving details, improving in-the-wild view synthesis quality and efficiency.

Findings

Achieves 4-5x reduction in energy consumption.

Produces photorealistic, geometrically coherent results.

Demonstrates robustness on in-the-wild image collections.

Abstract

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.