R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision

TL;DR

This survey reviews recent advances in robust 3D neural rendering and restoration techniques that handle real-world degradations, emphasizing the importance of 3D Low-Level Vision for reliable scene reconstruction in challenging conditions.

Contribution

It formalizes the degradation-aware rendering problem in 3D LLV and categorizes recent methods integrating low-level vision tasks into neural rendering frameworks.

Findings

Recent methods improve 3D reconstruction under noise and low-resolution conditions.

Integration of LLV tasks enhances robustness of neural rendering models.

Application domains include autonomous driving, AR/VR, and robotics.

Abstract

Neural rendering methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have achieved significant progress in photorealistic 3D scene reconstruction and novel view synthesis. However, most existing models assume clean and high-resolution (HR) multi-view inputs, which limits their robustness under real-world degradations such as noise, blur, low-resolution (LR), and weather-induced artifacts. To address these limitations, the emerging field of 3D Low-Level Vision (3D LLV) extends classical 2D Low-Level Vision tasks including super-resolution (SR), deblurring, weather degradation removal, restoration, and enhancement into the 3D spatial domain. This survey, referred to as R\textsuperscript{3}eVision, provides a comprehensive overview of robust rendering, restoration, and enhancement for 3D LLV by formalizing the degradation-aware rendering problem and identifying key challenges related to spatio-temporal consistency and ill-posed optimization. Recent methods that integrate LLV into neural rendering frameworks are categorized to illustrate how they enable high-fidelity 3D reconstruction under adverse conditions. Application domains such as autonomous driving, AR/VR, and robotics are also discussed, where reliable 3D perception from degraded inputs is critical. By reviewing representative methods, datasets, and evaluation protocols, this work positions 3D LLV as a fundamental direction for robust 3D content generation and scene-level reconstruction in real-world environments.