Radiance Meshes for Volumetric Reconstruction
Alexander Mai, Trevor Hedstrom, George Kopanas, Janne Kontkanen, Falko Kuester, Jonathan T. Barron
摘要
We introduce Radiance Meshes for representing radiance fields with constant density tetrahedral cells produced with a Delaunay tetrahedralization.Unlike a Voronoi diagram, a Delaunay tetrahedralization yields simple triangles that are natively supported by existing hardware. As such, our model is able to perform exact and fast volume rendering using both rasterization and ray-tracing. We introduce a new rasterization method that achieve faster rendering speeds than all prior radiance field representations (assuming an equivalent number of primitives and resolution) across a variety of platforms.Optimizing the positions of Delaunay vertices introduces topological discontinuities (edge flips). To solve this, we use a Zip-NeRF-style backbone which allows us to express a smoothly varying field even when the topology changes.Our rendering method exactly evaluates the volume rendering equation and enables high quality, real-time view synthesis on standard consumer hardware. Our tetrahedral meshes also lend themselves to a variety of exciting applications including fisheye lens distortion, physics-based simulation, editing, and mesh extraction.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Scalable GPU Construction of 3D Voronoi and Power DiagramsBernardo Taveira, Carl Lindström, Maryam Fatemi, Lars Hammarstrand 等SIGGRAPH 2026
- Distance Field Rasterization for End-to-End Mesh ReconstructionJinkai Cui, Kaiwen Song, Chumeng Niu, Juyong ZhangSIGGRAPH 2026
它引用的顶会 Paper24
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt 等NeurIPS 2021 · 被引用 2,500 次
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 被引用 1,421 次
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen 等CVPR 2022 · 被引用 1,237 次
相关 Paper
- BakedSDF: Meshing Neural SDFs for Real-Time View SynthesisLior Yariv, Peter Hedman, Christian Reiser, Dor Verbin 等SIGGRAPH 2023 · 被引用 177 次
- Delicate Textured Mesh Recovery from NeRF via Adaptive Surface RefinementJiaxiang Tang, Hang Zhou, Xiaokang Chen, Tianshu Hu 等ICCV 2023 · 被引用 162 次
- EVER: Exact Volumetric Ellipsoid Rendering for Real-Time View SynthesisAlexander Mai, Peter Hedman, George Kopanas, Dor Verbin 等ICCV 2025 · 被引用 8 次
- Radiant Foam: Real-Time Differentiable Ray TracingShrisudhan Govindarajan, Daniel Rebain, Kwang Moo Yi, Andrea TagliasacchiICCV 2025 · 被引用 14 次
- Learning Neural Light Fields with Ray-Space EmbeddingBenjamin Attal, Jia-Bin Huang, Michael Zollhöfer, Johannes Kopf 等CVPR 2022 · 被引用 75 次
