3D reconstruction from 2D image was extensively studied, training with depth supervision. To relax the dependence to costly-acquired datasets, we propose SceneRF, a self-supervised monocular scene reconstruction method using only posed image sequences for training. Fueled by the recent progress in neural radiance fields (NeRF) we optimize a radiance field though with explicit depth optimization and a novel probabilistic sampling strategy to efficiently handle large scenes. At inference, a single input image suffices to hallucinate novel depth views which are fused together to obtain 3D scene reconstruction. Thorough experiments demonstrate that we outperform all recent baselines for novel depth views synthesis and scene reconstruction, on indoor BundleFusion and outdoor SemanticKITTI. Our code is available at https://astra-vision.github.io/SceneRF.
翻译:为了放松对昂贵获得的数据集的依赖,我们建议SceenRF, 这是一种自我监督的单体场景重建方法,仅使用图像序列进行训练。由于神经光谱场(NERF)最近的进展,我们优化了光亮场,但以明确的深度优化和新颖的概率抽样策略来有效处理大场景。推断,单一输入图像足以让幻觉般的新深度视图融合在一起,以获得3D场景重建。索罗试验表明,我们超越了所有最新基线,在室内布德勒福松和室外的SmanticKTI,新深度视图合成和场景重建,我们的代码可在https://astra-vision.github.io/SceenRF查阅。</s>