NeuS is a novel neural surface reconstruction method that uses volume rendering to train a signed distance function (SDF) representation for high-fidelity 3D object and scene reconstruction from 2D image inputs. Unlike existing methods that require foreground masks or struggle with self-occlusions and thin structures, NeuS employs a new volume rendering scheme that ensures unbiased surface reconstruction. This scheme introduces an opaque density function and a weight function that are both occlusion-aware and unbiased in the first-order approximation of the SDF. Experiments on the DTU and BlendedMVS datasets demonstrate that NeuS outperforms state-of-the-art methods in terms of reconstruction quality, especially for complex structures and self-occlusions. The method also shows promise in handling thin structures and textureless objects, though further improvements are needed in these areas.NeuS is a novel neural surface reconstruction method that uses volume rendering to train a signed distance function (SDF) representation for high-fidelity 3D object and scene reconstruction from 2D image inputs. Unlike existing methods that require foreground masks or struggle with self-occlusions and thin structures, NeuS employs a new volume rendering scheme that ensures unbiased surface reconstruction. This scheme introduces an opaque density function and a weight function that are both occlusion-aware and unbiased in the first-order approximation of the SDF. Experiments on the DTU and BlendedMVS datasets demonstrate that NeuS outperforms state-of-the-art methods in terms of reconstruction quality, especially for complex structures and self-occlusions. The method also shows promise in handling thin structures and textureless objects, though further improvements are needed in these areas.