mlsanityData to 7 Oct 2026

FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions

arXiv 2203.16284 ↗First posted 30 Mar 2022cs.CV cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating the network multiple times per camera ray so that the high computational time forms a bottleneck for downstream applications. We address this problem by introducing a novel neural scene representation that we call the directional distance function (DDF). To this end, we learn a signed distance function (SDF) along with our DDF model to represent a class of shapes. Specifically, our DDF is defined on the unit sphere and predicts the distance to the surface along any given direction. Therefore, our DDF allows rendering images with just a single network evaluation per camera ray. Based on our DDF, we present a novel fast algorithm (FIRe) to reconstruct 3D shapes given a posed depth map. We evaluate our proposed method on 3D reconstruction from single-view depth images, where we empirically show that our algorithm reconstructs 3D shapes more accurately and it is more than 15 times faster (per iteration) than competing methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 37 of its 64 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

37 of 64 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
25 more
  1. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  2. 2020Convolutional Occupancy Networkscited by 760
  3. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  7. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  8. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  9. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  10. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  11. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  12. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  13. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  14. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  15. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  16. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  17. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  18. 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
  19. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  20. 2021TermiNeRF: Ray Termination Prediction for Efficient Neural Renderingcited by 70
  21. 2019Photometric Mesh Optimization for Video-Aligned 3D Object Reconstructioncited by 28
  22. 2021Representing 3D Shapes with Probabilistic Directed Distance Fieldscited by 21
  23. 2021Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstructioncited by 12
  24. 2021A Deep Signed Directional Distance Function for Object Shape Representationcited by 10
  25. 2021Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collectionscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 2; 2026: 1.

9 papers.

  1. 2023The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibilitycited by 11
  2. 2023Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representationscited by 5
  3. 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fieldscited by 5
  4. 2023MARF: The Medial Atom Ray Field Object Representationcited by 2
  5. 2025Mesh Compression with Quantized Neural Displacement Fieldscited by 1
  6. 2026Shape Representation using Gaussian Process mixture modelscited by 1
  7. 2024Probabilistic Directed Distance Fields for Ray-Based Shape Representationscited by 0
  8. 2024COBRA -- COnfidence score Based on shape Regression Analysis for method-independent quality assessment of object pose estimation from single imagescited by 0
  9. 2025Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residualscited by 0