ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution

2026-05-24

AI Summary

This work addresses the challenge of texture blurriness, ambiguous boundaries, and inter-view inconsistencies commonly observed in multi-view reconstruction from low-resolution images, which stem from missing high-frequency information. To tackle this, the authors propose a reliability-aware high-frequency modeling framework that explicitly distinguishes between regions requiring enhancement and those containing reliable high-frequency content. By fusing a geometry-guided detail-demand prior with a frequency-aware reliability map, the method generates a detail injection map that enables confidence-based selective high-frequency injection. The approach integrates spatially selective supervision, coarse-to-fine frequency regularization, and reliability-aware Gaussian densification, significantly improving both reconstruction fidelity and perceptual quality across multiple benchmarks while effectively suppressing inconsistent or unreliable details.

Abstract

Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and view-inconsistent details. Existing approaches either apply super-resolution guidance uniformly or localize enhancement regions based mainly on geometric sampling. However, they typically do not distinguish between two fundamentally different questions: where additional detail is needed, and whether the corresponding candidate high-frequency content is reliable enough to be internalized into a multi-view consistent 3D representation. In this paper, we propose a reliability-aware frequency modeling framework for low-resolution 3DGS reconstruction. The framework first estimates a geometry-guided detail-demand prior to locate regions that are likely under-detailed under low-resolution supervision. It then computes a frequency-aware reliability map to determine whether candidate high-frequency details are structurally supported, spectrally unresolved, and cross-view stable. Combining these signals yields a detail-injection map that guides where super-resolved details should be introduced during optimization. Based on this map, we design a unified optimization scheme comprising spatially selective supervision, coarse-to-fine frequency regularization, and reliability-aware Gaussian densification. This scheme controls where reliable details are injected, when high-frequency supervision is activated, and how unresolved yet reliable details are internalized into the Gaussian representation. Experiments on multiple benchmarks show improved fidelity and perceptual quality while suppressing unstable or view-inconsistent details.

Problem

• 3D Gaussian Splatting
• super-resolution
• high-frequency detail
• multi-view consistency
• low-resolution reconstruction

Innovation

• 3D Gaussian Splatting
• super-resolution
• confidence-guided
• high-frequency injection
• multi-view consistency