mlsanityData to 14 Oct 2026

NeMF: Inverse Volume Rendering with Neural Microflake Field

arXiv 2304.00782 ↗First posted 3 Apr 2023cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Recovering the physical attributes of an object's appearance from its images captured under an unknown illumination is challenging yet essential for photo-realistic rendering. Recent approaches adopt the emerging implicit scene representations and have shown impressive results.However, they unanimously adopt a surface-based representation,and hence can not well handle scenes with very complex geometry, translucent object and etc. In this paper, we propose to conduct inverse volume rendering, in contrast to surface-based, by representing a scene using microflake volume, which assumes the space is filled with infinite small flakes and light reflects or scatters at each spatial location according to microflake distributions. We further adopt the coordinate networks to implicitly encode the microflake volume, and develop a differentiable microflake volume renderer to train the network in an end-to-end way in principle.Our NeMF enables effective recovery of appearance attributes for highly complex geometry and scattering object, enables high-quality relighting, material editing, and especially simulates volume rendering effects, such as scattering, which is infeasible for surface-based approaches.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 31 of its 59 references that are in the map. First posted on arXiv 3 Apr 2023.

Builds on

31 of 59 references.

References · 31

  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. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  9. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  10. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  11. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  12. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
19 more
  1. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 203
  2. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  3. 2022Modeling Indirect Illumination for Inverse Renderingcited by 168
  4. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  5. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  6. 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 111
  7. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  8. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  9. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  10. 2020Neural Light Transport for Relighting and View Synthesiscited by 73
  11. 2020Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Imagescited by 65
  12. 2022Relighting4D: Neural Relightable Human from Videoscited by 41
  13. 2021Shape and Material Capture at Homecited by 36
  14. 2017Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lightingcited by 31
  15. 2019A Neural Rendering Framework for Free-Viewpoint Relightingcited by 27
  16. 2020Seeing the World in a Bag of Chipscited by 25
  17. 2020Object-based Illumination Estimation with Rendering-aware Neural Networkscited by 19
  18. 2020Deep SVBRDF Estimation on Real Materialscited by 15
  19. 2020Shape From Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracingcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 16; 2025: 6; 2026: 3.

34 papers.

Sort:

By area:

  1. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  2. 2024GS^3: Efficient Relighting with Triple Gaussian Splattingcited by 44
  3. 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
  4. 2024Ref-GS: Directional Factorization for 2D Gaussian Splattingcited by 29
  5. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  6. 2024RelitLRM: Generative Relightable Radiance for Large Reconstruction Modelscited by 23
  7. 2023Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracingcited by 22
  8. 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
  9. 2024Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splattingcited by 18
  10. 2024RNG: Relightable Neural Gaussianscited by 16
  11. 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fieldscited by 16
  12. 2023Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objectscited by 15
22 more
  1. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  2. 2023VQ-NeRF: Neural Reflectance Decomposition and Editing with Vector Quantizationcited by 8
  3. 2024BiGS: Bidirectional Gaussian Primitives for Relightable 3D Gaussian Splattingcited by 8
  4. 2023TraM-NeRF: Tracing Mirror and Near-Perfect Specular Reflections through Neural Radiance Fieldscited by 7
  5. 2024Interactive Rendering of Relightable and Animatable Gaussian Avatarscited by 6
  6. 2024AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstructioncited by 6
  7. 2024Many-Worlds Inverse Renderingcited by 3
  8. 2023RNA: Relightable Neural Assetscited by 2
  9. 2024PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularizationcited by 2
  10. 2025NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitivescited by 2
  11. 2025ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfercited by 2
  12. 2026LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windowscited by 2
  13. 2024Multi-times Monte Carlo Rendering for Inter-reflection Reconstructioncited by 1
  14. 2024UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representationcited by 1
  15. 2024Material Transforms from Disentangled NeRF Representationscited by 1
  16. 2026GTSR: Subsurface Scattering Awared 3D Gaussians for Translucent Surface Reconstructioncited by 1
  17. 2023Optimized View and Geometry Distillation from Multi-view Diffusercited by 0
  18. 2024Exploration and Improvement of Nerf-based 3D Scene Editing Techniquescited by 0
  19. 2025TensoIS: A Step Towards Feed-Forward Tensorial Inverse Subsurface Scattering for Perlin Distributed Heterogeneous Mediacited by 0
  20. 2025Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimizationcited by 0
  21. 2025GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Cameracited by 0
  22. 2026TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructionscited by 0