CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes

2026-05-27

AI Summary

This work addresses the challenge of achieving both high photorealism and metric accuracy in unbounded scenes with complex lighting and pose variations, where existing NeRF methods often fall short. The authors propose a multi-region-of-interest local reconstruction mechanism that automatically focuses on critical areas without requiring additional submodules. Their approach integrates collinear ray sampling, depth-aware local neighborhood point extraction, and a geometry-aware color aggregation strategy. This combination effectively suppresses surface artifacts and significantly enhances both geometric fidelity and visual quality. Extensive experiments demonstrate that the method outperforms state-of-the-art NeRF and SfM-MVS baselines in real-world, complex scenarios.

Abstract

Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and imperfect captures that current Neural Radiance Field (NeRF) pipelines only partly satisfy. This study adapts NeRF-based 3D reconstruction to multi-region of interest unbounded scenes to improve robustness to lighting and pose variation while enforcing metric accuracy suitable for digital-twin applications. Our approach introduces (i) automated local region localization/detection and reconstruction to seamlessly prioritize areas of interest without proliferating submodules, (ii) collinearity-enforcing ray sampling to learn smooth planar and curved surfaces, (iii) depth-localized neighborhood point extraction to suppress surface artifacts, and (iv) geometry-relevant color aggregation to mitigate lighting- and pose-caused variations. Results indicate superior performance of the proposed pipeline over the baseline NeRF models and established Structure from Motion (SfM) - Multi-View Stereo (MVS) solutions.

Problem

• 3D reconstruction
• unbounded scenes
• metric accuracy
• Neural Radiance Field
• photorealism

Innovation

• CLEAR-NeRF
• collinearity-enforcing ray sampling
• local-region reconstruction
• depth-localized neighborhood
• geometry-relevant color aggregation