# NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images Source: [NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images]() Collection index: [llms.txt]() Data updated: 2026-01-01T16:41:39.094Z Authors: Mingwu Zheng, Haiyu Zhang, Hongyu Yang, Di Huang Published: 2023-03-24T15:57:39.000Z ## Abstract Realistic face rendering from multi-view images is beneficial to various computer vision and graphics applications. Due to the complex spatially-varying reflectance properties and geometry characteristics of faces, however, it remains challenging to recover 3D facial representations both faithfully and efficiently in the current studies. This paper presents a novel 3D face rendering model, namely NeuFace, to learn accurate and physically-meaningful underlying 3D representations by neural rendering techniques. It naturally incorporates the neural BRDFs into physically based rendering, capturing sophisticated facial geometry and appearance clues in a collaborative manner. Specifically, we introduce an approximated BRDF integration and a simple yet new low-rank prior, which effectively lower the ambiguities and boost the performance of the facial BRDFs. Extensive experiments demonstrate the superiority of NeuFace in human face rendering, along with a decent generalization ability to common objects. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Facial Appearance Reconstruction on FaceScape Subject 1 (Rich Reflection)](): Facial Appearance Reconstruction; FaceScape Subject 1 (Rich Reflection); PSNR: 31.25. - [Facial Appearance Reconstruction on FaceScape Subject 2 (Moderate Reflection)](): Facial Appearance Reconstruction; FaceScape Subject 2 Moderate Reflection; PSNR: 31.87. - [Facial Geometry Reconstruction on FaceScape Subject 1 (Rich Reflection)](): Facial Geometry Reconstruction; FaceScape Subject 1 (Rich Reflection); Chamfer Distance: 0.447. - [Facial Geometry Reconstruction on FaceScape Subject 2 Moderate Reflection](): Facial Geometry Reconstruction; FaceScape Subject 2 Moderate Reflection; Chamfer Distance: 0.481. - [Facial Appearance Reconstruction on FaceScape Subject 3 (Low Reflection)](): Facial Appearance Reconstruction; FaceScape Subject 3 (Low Reflection); PSNR: 30.92. - [Facial Geometry Reconstruction on FaceScape Subject 3 (Low Reflection)](): Facial Geometry Reconstruction; FaceScape Subject 3 (Low Reflection); Chamfer Distance: 0.533. - [3D Face Reconstruction and Decomposition on FaceScape 3 views sparse views](): 3D Face Reconstruction and Decomposition; FaceScape 3 views sparse views; PSNR: 23.54. - [3D Face Reconstruction and Decomposition on FaceScape 5 views (sparse views)](): 3D Face Reconstruction and Decomposition; FaceScape 5 views (sparse views); PSNR: 25.81. - [3D Face Reconstruction and Decomposition on FaceScape 10 views (sparse views)](): 3D Face Reconstruction and Decomposition; FaceScape 10 views (sparse views); PSNR: 27.19. ## Original sources and implementation [Original paper]() [PDF]()