cs.CVNov 19, 2026

VideoRNG: Relightable Neural Gaussians from Generative Video Models

Authors: Bowen Xue, Saeed Hadadan, Fabrice Rousselle, Ravi Ramamoorthi, Zahra Montazeri, Miloš Hašan

Organizations: NVIDIA · University of Manchester · University of California, San Diego

Abstract

Generating realistic 3D assets remains constrained by classical representations: surface meshes and compact physically based materials struggle to express objects whose appearance arises from fine geometry or complex light transport, while existing Gaussian-splatting generators typically bake fixed illumination into appearance. We introduce VideoRNG, a two-stage method that generates complete, relightable 3D assets from a text prompt or a single image without prescribing a mesh or analytic material model. A video generator fine-tuned from a pretrained video diffusion backbone first produces a structured RGBA turntable sequence under a known pose, camera, and illumination. A feed-forward large reconstruction model initialized from a pretrained video diffusion backbone then maps the video-VAE latent frames of selected turntable frames directly to millions of anisotropic Gaussians with learned neural appearance features. A shared directional decoder and stochastic Gaussian ray tracer turn this representation, which we call ray-traced Relightable Neural Gaussians (rtRNG), into radiance under novel viewpoints and illumination. To preserve high-frequency appearance while learning geometry, we introduce depth-anchored appearance training, and we make million-Gaussian reconstruction practical through foreground token selection and cost-aware distributed sampling. VideoRNG generates complex assets such as fur, feathers, and spider webs that can be interactively rendered, relit, and integrated into scenes.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. F-RNG: Feed-Forward Relightable Neural Gaussians

    May 25, 2026Guangming Fu, Jiahui Fan, Jian Yang +23D Gaussian Splatting3D Reconstruction

  2. Luce: Relightable Gaussians for 3D Asset Generation

    Aug 25, 2026Mayank Singh, Michele Stoppa, Alvise Memo +73D Gaussian Splatting3D Asset Generation

  3. TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos

    Mar 18, 2026Yan Zeng, Haoran Jiang, Kaixin Yao +43D Texture Generation3D Asset Generation