SAR3D: Autoregressive 3D object generation and understanding via multi-scale 3D VQVAE

Y Chen, Y Lan, S Zhou, T Wang, XI Pan - arxiv preprint arxiv:2411.16856, 2024 - arxiv.org
Autoregressive models have demonstrated remarkable success across various fields, from
large language models (LLMs) to large multimodal models (LMMs) and 2D content …

Material Anything: Generating Materials for Any 3D Object via Diffusion

X Huang, T Wang, Z Liu, Q Wang - arxiv preprint arxiv:2411.15138, 2024 - arxiv.org
We present Material Anything, a fully-automated, unified diffusion framework designed to
generate physically-based materials for 3D objects. Unlike existing methods that rely on …

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion

Z He, T Wang, X Huang, X Pan, Z Liu - arxiv preprint arxiv:2412.09593, 2024 - arxiv.org
Recovering the geometry and materials of objects from a single image is challenging due to
its under-constrained nature. In this paper, we present Neural LightRig, a novel framework …