arXiv Computer Vision
RefRef: A Dataset and Benchmark for Reconstructing Refractive and Reflective Objects
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 28
RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
RefracGS is a novel framework for generating novel views through refractive water surfaces. It jointly reconstructs the water surface using a neural height field and the underlying scene with a 3D Gaussian field, employing refraction‑aware Gaussian ray tracing based on Snell’s law. The method achieves high‑fidelity view synthesis, outperforms prior refractive approaches, and offers 15× faster training with real‑time rendering at 200 FPS.
arXiv Computer Vision
Sep 1
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing
arXiv:2608.29269v1 Announce Type: new Abstract: Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts unde...
Hugging Face Trending Papers
Aug 6
Floating Radiance Networks
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their versatility and integration with conventional graphics workflows. We introduce Floating Radiance Networks (FlaRe), a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions.
arXiv Computer Vision
4d ago
Light Field Primitive for Novel View Synthesis
arXiv:2609.31198v1 Announce Type: new Abstract: We present Light Field Primitives (LFP), a formulation for novel view synthesis that replaces the dense ray database with a compact set of differentiab...
arXiv Machine Learning
Sep 10
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives
arXiv:2609.05738v1 Announce Type: cross Abstract: We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, th...
arXiv AI
Jun 3
Ref-DGS: Reflective Dual Gaussian Splatting
arXiv:2603. 07664v3 Announce Type: replace-cross Abstract: The reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis.