EdgeNeRF: Edge-Guided Regularization for Neural Radiance Fields from Sparse Views

2026-01-04

Chinese Conference on Pattern Recognition and Computer Vision

AI Summary

This work addresses the challenge of geometric artifacts in Neural Radiance Field (NeRF) reconstruction under sparse-view settings, where existing methods often suffer from blurred boundary details due to global depth regularization. To mitigate this issue, we propose EdgeNeRF, a plug-and-play framework that leverages image edge detection to guide local depth and normal regularization—applying constraints only in non-edge regions. This strategy effectively preserves high-frequency boundary details while enhancing geometric consistency. EdgeNeRF seamlessly integrates into existing NeRF pipelines with negligible additional training overhead. Extensive experiments on the LLFF and DTU datasets demonstrate that EdgeNeRF significantly outperforms current approaches, successfully suppressing reconstruction artifacts while maintaining sharp and accurate geometric structures.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Other Foundations of Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Neural Radiance Fields (NeRF) achieve remarkable performance in dense multi-view scenarios, but their reconstruction quality degrades significantly under sparse inputs due to geometric artifacts. Existing methods utilize global depth regularization to mitigate artifacts, leading to the loss of geometric boundary details. To address this problem, we propose EdgeNeRF, an edge-guided sparse-view 3D reconstruction algorithm. Our method leverages the prior that abrupt changes in depth and normals generate edges. Specifically, we first extract edges from input images, then apply depth and normal regularization constraints to non-edge regions, enhancing geometric consistency while preserving high-frequency details at boundaries. Experiments on LLFF and DTU datasets demonstrate EdgeNeRF's superior performance, particularly in retaining sharp geometric boundaries and suppressing artifacts. Additionally, the proposed edge-guided depth regularization module can be seamlessly integrated into other methods in a plug-and-play manner, significantly improving their performance without substantially increasing training time. Code is available at https://github.com/skyhigh404/edgenerf.

Problem

• Neural Radiance Fields
• sparse views
• geometric artifacts
• boundary details
• 3D reconstruction

Innovation

• Edge-guided regularization
• Neural Radiance Fields
• Sparse-view reconstruction
• Geometric boundary preservation
• Plug-and-play module