mlsanityData to 14 Oct 2026

NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images

arXiv 2303.14092 ↗First posted 24 Mar 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 29 of its 65 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

29 of 65 references.

References · 29

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  7. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  11. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  12. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
17 more
  1. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  2. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  3. 2021Advances in Neural Renderingcited by 365
  4. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  5. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  6. 20193D Morphable Face Models -- Past, Present and Futurecited by 270
  7. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  8. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  9. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 180
  10. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  11. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  12. 2022NeILF: Neural Incident Light Field for Physically-based Material Estimationcited by 105
  13. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  14. 2022Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illuminationcited by 41
  15. 2021NeLF: Neural Light-transport Field for Portrait View Synthesis and Relightingcited by 38
  16. 2019A Neural Rendering Framework for Free-Viewpoint Relightingcited by 27
  17. 2022EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyescited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 3; 2025: 2; 2026: 2.

12 papers.

  1. 2023Towards Practical Capture of High-Fidelity Relightable Avatarscited by 34
  2. 2023Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatarcited by 14
  3. 2023ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 10
  4. 2023High-Quality Facial Geometry and Appearance Capture at Homecited by 9
  5. 2023SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Imagescited by 4
  6. 2024PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularizationcited by 2
  7. 2024Monocular Facial Appearance Capture in the Wildcited by 2
  8. 2024Learning to Decouple the Lights for 3D Face Texture Modelingcited by 1
  9. 2025WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Renderingcited by 1
  10. 2026From Blurry to Believable: Enhancing Low-quality Talking Heads with 3D Generative Priorscited by 1
  11. 2025GLVD: Guided Learned Vertex Descentcited by 0
  12. 2026MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modelingcited by 0