Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 95% Match Research Paper 3D Artists,Game Developers,VFX Artists,Computer Graphics Researchers,AI Researchers 3 weeks ago

SViM3D: Stable Video Material Diffusion for Single Image 3D Generation

computer-vision › 3d-vision
📄 Abstract

Abstract: We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently. However, reflectance is still represented by simple material models or needs to be estimated in additional steps to enable relighting and controlled appearance edits. We extend a latent video diffusion model to output spatially varying PBR parameters and surface normals jointly with each generated view based on explicit camera control. This unique setup allows for relighting and generating a 3D asset using our model as neural prior. We introduce various mechanisms to this pipeline that improve quality in this ill-posed setting. We show state-of-the-art relighting and novel view synthesis performance on multiple object-centric datasets. Our method generalizes to diverse inputs, enabling the generation of relightable 3D assets useful in AR/VR, movies, games and other visual media.

Key Contributions

Presents SViM3D, a framework extending latent video diffusion models to predict multi-view consistent Physically Based Rendering (PBR) materials from a single image. It enables relighting and controlled appearance edits by jointly generating PBR parameters and surface normals, acting as a neural prior for 3D asset generation.

Business Value

Significantly streamlines the creation of realistic 3D assets with controllable materials, accelerating workflows in game development, VFX, and AR/VR content creation.