Pseudo-View Enhancement via Confidence Fusion for Unposed Sparse-View Reconstruction

TL;DR

This paper presents a novel framework for unposed sparse-view outdoor 3D scene reconstruction that improves quality and consistency by bidirectional pseudo frame restoration and Gaussian scene perception management.

Contribution

It introduces a bidirectional pseudo frame restoration method and scene perception Gaussian management strategy, enhancing reconstruction quality under extreme view sparsity.

Findings

Significant improvements in fidelity and stability on outdoor benchmarks.

Enhanced geometric consistency and artifact suppression.

Effective handling of extreme view sparsity in outdoor scenes.

Abstract

3D scene reconstruction under unposed sparse viewpoints is a highly challenging yet practically important problem, especially in outdoor scenes due to complex lighting and scale variation. With extremely limited input views, directly utilizing diffusion model to synthesize pseudo frames will introduce unreasonable geometry, which will harm the final reconstruction quality. To address these issues, we propose a novel framework for sparse-view outdoor reconstruction that achieves high-quality results through bidirectional pseudo frame restoration and scene perception Gaussian management. Specifically, we introduce a bidirectional pseudo frame restoration method that restores missing content by diffusion-based synthesis guided by adjacent frames with a lightweight pseudo-view deblur model and confidence mask inference algorithm. Then we propose a scene perception Gaussian management strategy that optimize Gaussians based on joint depth-density information. These designs significantly enhance reconstruction completeness, suppress floating artifacts and improve overall geometric consistency under extreme view sparsity. Experiments on outdoor benchmarks demonstrate substantial gains over existing methods in both fidelity and stability.