# NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections

arXiv: https://arxiv.org/abs/2405.14871 · HTML: https://mlsanity.com/paper/2405.14871/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [ReLU Fields: The Little Non-linearity That Could](https://mlsanity.com/paper/2205.10824/) (2022)
- [ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting](https://mlsanity.com/paper/2303.13022/) (2023)
- [Neural Microfacet Fields for Inverse Rendering](https://mlsanity.com/paper/2303.17806/) (2023)
- [SpecNeRF: Gaussian Directional Encoding for Specular Reflections](https://mlsanity.com/paper/2312.13102/) (2023)
- [UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections](https://mlsanity.com/paper/2312.13285/) (2023)
- [NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination](https://mlsanity.com/paper/2304.08757/) (2023)

## Built on by (most cited first, 30 of 33)

- [EnvGS: Modeling View-Dependent Appearance with Environment Gaussian](https://mlsanity.com/paper/2412.15215/) (2024)
- [IllumiNeRF: 3D Relighting Without Inverse Rendering](https://mlsanity.com/paper/2406.06527/) (2024)
- [SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes](https://mlsanity.com/paper/2410.17249/) (2024)
- [Sharp Monocular View Synthesis in Less Than a Second](https://mlsanity.com/paper/2512.10685/) (2025)
- [LightSwitch: Multi-view Relighting with Material-guided Diffusion](https://mlsanity.com/paper/2508.06494/) (2025)
- [Geometry Field Splatting with Gaussian Surfels](https://mlsanity.com/paper/2411.17067/) (2024)
- [Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation](https://mlsanity.com/paper/2412.15211/) (2024)
- [Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere](https://mlsanity.com/paper/2512.14180/) (2025)
- [ROGR: Relightable 3D Objects using Generative Relighting](https://mlsanity.com/paper/2510.03163/) (2025)
- [ProbeSDF: Light Field Probes for Neural Surface Reconstruction](https://mlsanity.com/paper/2412.10084/) (2024)
- [Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis](https://mlsanity.com/paper/2505.00135/) (2025)
- [Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction](https://mlsanity.com/paper/2501.11020/) (2025)
- [Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering](https://mlsanity.com/paper/2507.06103/) (2025)
- [Surf-NeRF: Surface Regularised Neural Radiance Fields](https://mlsanity.com/paper/2411.18652/) (2024)
- [MADrive: Memory-Augmented Driving Scene Modeling](https://mlsanity.com/paper/2506.21520/) (2025)
- [NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives](https://mlsanity.com/paper/2501.04074/) (2025)
- [Fillerbuster: Unified Generative Scene Completion Model for Casual Captures](https://mlsanity.com/paper/2502.05175/) (2025)
- [Can NeRFs See without Cameras?](https://mlsanity.com/paper/2505.22441/) (2025)
- [RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting](https://mlsanity.com/paper/2605.18263/) (2026)
- [RefRef: A Dataset and Benchmark for Reconstructing Refractive and Reflective Objects](https://mlsanity.com/paper/2505.05848/) (2025)
- [TR-Gaussians: High-fidelity Real-time Rendering of Planar Transmission and Reflection with 3D Gaussian Splatting](https://mlsanity.com/paper/2511.13009/) (2025)
- [Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light](https://mlsanity.com/paper/2512.06080/) (2025)
- [TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering](https://mlsanity.com/paper/2605.10705/) (2026)
- [Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction](https://mlsanity.com/paper/2511.21098/) (2025)
- [HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting](https://mlsanity.com/paper/2512.08334/) (2025)
- [FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention Adaptation](https://mlsanity.com/paper/2512.09617/) (2025)
- [TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing](https://mlsanity.com/paper/2512.10095/) (2025)
- [ShinyNeRF: Digitizing Anisotropic Appearance in Neural Radiance Fields](https://mlsanity.com/paper/2512.21692/) (2025)
- [Ref-DGS: Reflective Dual Gaussian Splatting](https://mlsanity.com/paper/2603.07664/) (2026)
- [PhyGaP: Physically-Grounded Gaussians with Polarization Cues](https://mlsanity.com/paper/2603.14001/) (2026)

## Abstract (arXiv)

Neural Radiance Fields (NeRFs) typically struggle to reconstruct and render highly specular objects, whose appearance varies quickly with changes in viewpoint. Recent works have improved NeRF's ability to render detailed specular appearance of distant environment illumination, but are unable to synthesize consistent reflections of closer content. Moreover, these techniques rely on large computationally-expensive neural networks to model outgoing radiance, which severely limits optimization and rendering speed. We address these issues with an approach based on ray tracing: instead of querying an expensive neural network for the outgoing view-dependent radiance at points along each camera ray, our model casts reflection rays from these points and traces them through the NeRF representation to render feature vectors which are decoded into color using a small inexpensive network. We demonstrate that our model outperforms prior methods for view synthesis of scenes containing shiny objects, and that it is the only existing NeRF method that can synthesize photorealistic specular appearance and reflections in real-world scenes, while requiring comparable optimization time to current state-of-the-art view synthesis models.