Skip to yearly menu bar Skip to main content


Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

Guocheng Qian · Jinjie Mai · Abdullah Hamdi · Jian Ren · Aliaksandr Siarohin · Bing Li · Hsin-Ying Lee · Ivan Skorokhodov · Peter Wonka · Sergey Tulyakov · Bernard Ghanem

Halle B #253
[ ] [ Project Page ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT


We present ``Magic123'', a two-stage coarse-to-fine approach for high-quality, textured 3D mesh generation from a single image in the wild using both 2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference-view supervision and novel-view guidance by a joint 2D and 3D diffusion prior. We introduce a trade-off parameter between the 2D and 3D priors to control the details and 3D consistencies of the generation. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on diverse synthetic and real-world images.

Chat is not available.