TY - GEN
T1 - Make-It-3D
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
AU - Tang, Junshu
AU - Wang, Tengfei
AU - Zhang, Bo
AU - Zhang, Ting
AU - Yi, Ran
AU - Ma, Lizhuang
AU - Chen, Dong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the underlying 3D geometry while simultaneously hallucinating unseen textures. To address this challenge, we leverage prior knowledge from a well-trained 2D diffusion model to act as 3D-aware supervision for 3D creation. Our approach, Make-It-3D, employs a two-stage optimization pipeline: the first stage optimizes a neural radiance field by incorporating constraints from the reference image at the frontal view and diffusion prior at novel views; the second stage transforms the coarse model into textured point clouds and further elevates the realism with diffusion prior while leveraging the high-quality textures from the reference image. Extensive experiments demonstrate that our method outperforms prior works by a large margin, resulting in faithful reconstructions and impressive visual quality. Our method presents the first attempt to achieve high-quality 3D creation from a single image for general objects and enables various applications such as text-to-3D creation and texture editing.
AB - In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the underlying 3D geometry while simultaneously hallucinating unseen textures. To address this challenge, we leverage prior knowledge from a well-trained 2D diffusion model to act as 3D-aware supervision for 3D creation. Our approach, Make-It-3D, employs a two-stage optimization pipeline: the first stage optimizes a neural radiance field by incorporating constraints from the reference image at the frontal view and diffusion prior at novel views; the second stage transforms the coarse model into textured point clouds and further elevates the realism with diffusion prior while leveraging the high-quality textures from the reference image. Extensive experiments demonstrate that our method outperforms prior works by a large margin, resulting in faithful reconstructions and impressive visual quality. Our method presents the first attempt to achieve high-quality 3D creation from a single image for general objects and enables various applications such as text-to-3D creation and texture editing.
UR - https://www.scopus.com/pages/publications/85171637616
U2 - 10.1109/ICCV51070.2023.02086
DO - 10.1109/ICCV51070.2023.02086
M3 - 会议稿件
AN - SCOPUS:85171637616
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 22762
EP - 22772
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 2 October 2023 through 6 October 2023
ER -