MicroDreamer Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction

MicroDreamer : Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction

Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and the limitation of optimization confined to latent space. This...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 19. Aug.
Auteur principal: Chen, Luxi (Auteur)
Autres auteurs: Wang, Zhengyi, Zhou, Zihan, Gao, Tingting, Su, Hang, Zhu, Jun, Li, Chongxuan
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM391447785
003 DE-627
005 20250828002342.0
007 cr uuu---uuuuu
008 250820s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3600494  |2 doi 
028 5 2 |a pubmed25n1546.xml 
035 |a (DE-627)NLM391447785 
035 |a (NLM)40828710 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Luxi  |e verfasserin  |4 aut 
245 1 0 |a MicroDreamer  |b Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 19.08.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and the limitation of optimization confined to latent space. This paper introduces score-based iterative reconstruction (SIR), an efficient and general algorithm mimicking a differentiable 3D reconstruction process to reduce the NFEs and enable optimization in pixel space. Given a single set of images sampled from a multi-view score-based diffusion model, SIR repeatedly optimizes 3D parameters, unlike the single-step optimization in SDS. With other improvements in training, we present an efficient approach called MicroDreamer that generally applies to various 3D representations and 3D generation tasks. In particular, MicroDreamer is 5-20 times faster than SDS in generating neural radiance field while retaining a comparable performance and takes about 20 seconds to create meshes from 3D Gaussian splatting on a single A100 GPU, halving the time of the fastest optimization-based baseline DreamGaussian with significantly superior performance compared to the measurement standard deviation. Our code is available at https://github.com/ML-GSAI/MicroDreamer 
650 4 |a Journal Article 
700 1 |a Wang, Zhengyi  |e verfasserin  |4 aut 
700 1 |a Zhou, Zihan  |e verfasserin  |4 aut 
700 1 |a Gao, Tingting  |e verfasserin  |4 aut 
700 1 |a Su, Hang  |e verfasserin  |4 aut 
700 1 |a Zhu, Jun  |e verfasserin  |4 aut 
700 1 |a Li, Chongxuan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 19. Aug.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:19  |g month:08 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3600494  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 19  |c 08