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

2026-02-24

AI Summary

This work addresses the challenges of geometric distortion and poor reconstruction quality in outdoor scene 3D reconstruction from sparse, pose-free viewpoints. To this end, we propose a novel approach that integrates bidirectional pseudo-view synthesis with scene-aware Gaussian regulation. Specifically, a lightweight deblurring module guided by a diffusion model generates high-fidelity pseudo-views, while a depth-density joint optimization strategy refines Gaussian parameters to effectively suppress floating artifacts and enhance geometric consistency. Extensive experiments on multiple outdoor benchmark datasets demonstrate that our method significantly outperforms existing state-of-the-art techniques, achieving substantial improvements in both reconstruction fidelity and stability.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• sparse-view reconstruction
• unposed views
• 3D scene reconstruction
• outdoor scenes
• pseudo-view synthesis

Innovation

• pseudo-view enhancement
• confidence fusion
• sparse-view reconstruction
• Gaussian splatting
• diffusion-based synthesis