TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing
By: Jiachen Tao , Junyi Wu , Haoxuan Wang and more
Potential Business Impact:
Makes computer-generated reflections look real.
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.
Similar Papers
HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting
CV and Pattern Recognition
Makes 3D scenes with shiny things look real.
Flux4D: Flow-based Unsupervised 4D Reconstruction
CV and Pattern Recognition
Builds 3D worlds from videos in seconds.
TR-Gaussians: High-fidelity Real-time Rendering of Planar Transmission and Reflection with 3D Gaussian Splatting
Graphics
Makes computer images show glass reflections realistically.