TY  - JOUR
TI  - DreamFusion: Text-to-3D Using 2D Diffusion
AU  - Poole, B.
AU  - Jain, A.
AU  - Barron, J. T.
AU  - Mildenhall, B.
PY  - 2023
DA  - 2023///
JO  - ICLR 2023
AB  - Poole et al. (2022, published ICLR 2023) present DreamFusion, the first method to generate 3D assets from text descriptions by distilling knowledge from a pretrained 2D diffusion model into a NeRF via a novel Score Distillation Sampling loss. The approach requires no 3D training data and generalises to arbitrary text prompts. Recognised as an ICLR 2023 Outstanding Paper, DreamFusion established the text-to-3D category and its Score Distillation Sampling technique directly underlies subsequent tools entering animation and game-art production pipelines.
KW  - generative-ai
KW  - 3d-generation
KW  - image-generation
KW  - curriculum-design
UR  - https://arxiv.org/abs/2209.14988
LA  - en
ER  -