Skip to content
Preprint

Luce: Relightable Gaussians for 3D Asset Generation

Aug 2026 · 0 citations · 65 references
Computer Science

TL;DR

Luce is proposed, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for albedo, metallic-roughness, and surface normals to achieve state-of-the-art single-image-to-3D generation.

Abstract

High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. However, preserving fine detail across the physically based rendering (PBR) modalities needed for relighting remains challenging. To address this, we propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for albedo, metallic-roughness, and surface normals. A variational autoencoder compresses this representation into a unified material-aware latent space. A rectified-flow transformer generates this latent from a single image using multi-layer features from a pretrained image encoder that preserve both semantic context and fine spatial detail. The latent is then decoded into relightable PBR Gaussians and an optional textured mesh with a tangent-space normal map. On Toys4K, Luce achieves state-of-the-art single-image-to-3D generation, improving FID by 28% over the strongest baseline. We further evaluate Luce on a benchmark of AI-generated images depicting diverse subjects and materials, where it improves the CLIP image-alignment score over the best baseline (0.8519 vs. 0.8299). Luce generates relightable, geometrically accurate, and materially faithful assets that preserve fine details such as text, logos, and inscriptions.

View source

Similar papers

Preprint Oct 2026

SUPRA-TEX: 3D Generation with Super-Aligned Texture

Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image. Existing methods either introduce artifacts when fusing inconsistent multi-view predictions or struggle to preserve fine details through implicit image-feature conditi...

Chen Yang, Jie-Min Fang, Fanpeng Meng et al. · 2 citations
Preprint Sep 2026

LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting

LightBridge is presented, a feed-forward generative framework for controllable relighting of complete 3DGS assets in a single pass and efficient single-pass prediction of complete relit 3DGS assets without scene-specific optimization.

Heng Cao, Pan-Hao Cheng, Huang-Sheng Du et al. · 0 citations
Sep 2026

OmniFabric: Coherent UV Space Texture Synthesis for 3D Garment Reconstruction

Automated generation of production-ready 3D garment assets from a single image is a central challenge in digital content creation. While recent generative models have significantly advanced 3D geometry reconstruction, synthesizing high-quality textures remains a bottleneck. Existing methods often bake environmental ill...

Di Huang, Yuan-Hao Wang, Cheng Zhang et al. · 0 citations
Preprint Aug 2026

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion

DiGS-Avatar is proposed, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design, and introduces a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion stude...

Jiakun Li, Li Fang, Hao Zhu et al. · 0 citations
Preprint Aug 2026

SpatialCrafter: Single Image World Modeling with Generative 3D Proxies

SpatialCrafter is presented, a novel two-stage framework that addresses explorable image-to-scene generation issues by introducing a global 3D proxy for high-fidelity image-to-scene generation and appearance refinement and introduces Parallel Geometry Injection and Proxy-Aware Corruption training strategies.

Chuan Fang, Lingteng Qiu, Yixun Liang et al. · 3 citations
Preprint Aug 2026

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view generation for unobserved regions and geometric consistency, providing both geometrically aligned novel views and sharp depth estimates. Our approach builds on 3D Gaussian spl...

Giuseppe Stracquadanio, Kevin Raj, Julia Grabinski et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.