TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing
Not on the map. Why?
Abstract (arXiv)
We present TraceFlow, a novel framework for high-fidelity rendering of dynamic specular scenes by addressing two key challenges: precise reflection direction estimation and physically accurate reflection modeling. To achieve this, we propose a Residual Material-Augmented 2D Gaussian Splatting representation that models dynamic geometry and material properties, allowing accurate reflection ray computation. Furthermore, we introduce a Dynamic Environment Gaussian and a hybrid rendering pipeline that decomposes rendering into diffuse and specular components, enabling physically grounded specular synthesis via rasterization and ray tracing. Finally, we devise a coarse-to-fine training strategy to improve optimization stability and promote physically meaningful decomposition. Extensive experiments on dynamic scene benchmarks demonstrate that TraceFlow outperforms prior methods both quantitatively and qualitatively, producing sharper and more realistic specular reflections in complex dynamic environments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 61 of its 69 references that are in the map. First posted on arXiv 10 Dec 2025.
Builds on
61 of 69 references.
References · 61
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
38 more
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2020Neural Sparse Voxel Fieldscited by 959
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
- 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
- 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
- 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 471
- 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
- 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
- 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
- 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
- 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
- 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
- 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
- 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
- 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 217
- 2023Robust Dynamic Radiance Fieldscited by 194
- 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
- 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 111
- 2024Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videoscited by 97
- 2023GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesiscited by 95
- 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 74
- 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 69
- 20243DGS.zip: A survey on 3D Gaussian Splatting Compression Methodscited by 69
- 2023Forward Flow for Novel View Synthesis of Dynamic Scenescited by 68
- 20243D Gaussian Splatting with Deferred Reflectioncited by 63
- 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 63
- 2024IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracingcited by 54
- 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
- 2024GS^3: Efficient Relighting with Triple Gaussian Splattingcited by 44
- 20243DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardtcited by 43
- 2024EnvGS: Modeling View-Dependent Appearance with Environment Gaussiancited by 35
- 2024NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflectionscited by 33
50 most cited of 61 All 61 (JSON)
Built on by
Not cited yet.