提出新模型Is-NeRF，让模糊图像也能还原清晰3D场景。
Is-NeRF: In-scattering Neural Radiance Field for Blurred Images
- 用散射建模替代直线渲染，显式处理复杂光路。
- 在真实模糊图像上生成高保真、几何精确的3D画面。
- 适合处理运动模糊等复杂现实场景的重建任务。
神经辐射场（NeRF）因其出色的隐式3D表示和逼真的新视角合成能力而备受关注。现有方法普遍采用直线体积渲染，难以应对复杂的光路情况，并在训练中引入几何歧义，尤其在处理运动模糊图像时表现明显。为此，本文提出一种新型去模糊神经辐射场Is-NeRF，通过在真实环境中显式建模光路，将六种常见光传播现象统一为一种散射表示，构建了适应复杂光路的新散射感知体积渲染流程。同时，设计自适应学习策略，自动确定散射方向与采样间隔，以捕捉更精细的物体细节。所提网络联合优化NeRF参数、散射参数与相机运动，从模糊图像中恢复细粒度场景表示。全面评估表明，该方法能有效处理复杂真实场景，在生成高保真图像并保留准确几何细节方面优于当前最优方法。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images. To address these challenges, this work proposes a novel deblur neural radiance field, Is-NeRF, featuring explicit lightpath modeling in real-world environments. By unifying six common light propagation phenomena through an in-scattering representation, we establish a new scattering-aware volume rendering pipeline adaptable to complex lightpaths. Additionally, we introduce an adaptive learning strategy that enables autonomous determining of scattering directions and sampling intervals to capture finer object details. The proposed network jointly optimizes NeRF parameters, scattering parameters, and camera motions to recover fine-grained scene representations from blurry images. Comprehensive evaluations demonstrate that it effectively handles complex real-world scenarios, outperforming state-of-the-art approaches in generating high-fidelity images with accurate geometric details.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。