Volumetric Rendering with Baked Quadrature Fields
Not on the map. Why?
Abstract (arXiv)
We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that enables fast inference by utilizing textured polygons. Despite the high-quality novel view rendering that NeRF provides, a critical limitation is that it relies on volume rendering that can be computationally expensive and does not utilize the advancements in modern graphics hardware. Many existing methods fall short when it comes to modelling volumetric effects as they rely purely on surface rendering. We thus propose to model the scene with polygons, which can then be used to obtain the quadrature points required to model volumetric effects, and also their opacity and colour from the texture. To obtain such polygonal mesh, we train a specialized field whose zero-crossings would correspond to the quadrature points when volume rendering, and perform marching cubes on this field. We then perform ray-tracing and utilize the ray-tracing shader to obtain the final colour image. Our method allows an easy integration with existing graphics frameworks allowing rendering speed of over 100 frames-per-second for a 1920×1080 image, while still being able to represent non-opaque objects.
Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 2 Dec 2023.
Builds on
40 of 57 references.
References · 40
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
- 2021Volume Rendering of Neural Implicit Surfacescited by 996
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
- 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
28 more
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
- 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
- 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
- 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
- 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
- 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
- 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
- 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
- 2020State of the Art on Neural Renderingcited by 278
- 2021Urban Radiance Fieldscited by 263
- 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
- 2020Free View Synthesiscited by 231
- 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 221
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
- 2020Stable View Synthesiscited by 165
- 2020DeRF: Decomposed Radiance Fieldscited by 163
- 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
- 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
- 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 85
- 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
- 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64
- 2022nerf2nerf: Pairwise Registration of Neural Radiance Fieldscited by 39
- 2023VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesiscited by 25
- 2023NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objectscited by 14
- 2023NeRF Revisited: Fixing Quadrature Instability in Volume Renderingcited by 10
- 2023αSurf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacitycited by 4
Built on by
Citing papers per year: 2024: 4; 2025: 4; 2026: 1.
9 papers.
- 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 88
- 2025Radiant Foam: Real-Time Differentiable Ray Tracingcited by 34
- 2024Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshescited by 5
- 2025Content-Aware Texturing for Gaussian Splattingcited by 5
- 2025Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometriescited by 4
- 2024GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Accelerationcited by 3
- 2024From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuScited by 2
- 2026DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimizationcited by 1
- 2025Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networkscited by 0
- 2026DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization1 Apr 2026
- 2025Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries15 Dec 2025
- 2025Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks15 Dec 2025
- 2025Content-Aware Texturing for Gaussian Splatting2 Dec 2025
- 2025Radiant Foam: Real-Time Differentiable Ray Tracing3 Feb 2025
- 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting17 Dec 2024
- 2024From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuS8 Nov 2024
- 2024GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration19 Oct 2024
- 2024Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes4 Sep 2024