MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916673192198144 |
|---|---|
| author | Yildirim, Ahmet Burak Aydogdu, Mustafa Utku Ceylan, Duygu Dundar, Aysegul |
| author_facet | Yildirim, Ahmet Burak Aydogdu, Mustafa Utku Ceylan, Duygu Dundar, Aysegul |
| contents | We introduce MD-ProjTex, a method for fast and consistent text-guided texture generation for 3D shapes using pretrained text-to-image diffusion models. At the core of our approach is a multi-view consistency mechanism in UV space, which ensures coherent textures across different viewpoints. Specifically, MD-ProjTex fuses noise predictions from multiple views at each diffusion step and jointly updates the per-view denoising directions to maintain 3D consistency. In contrast to existing state-of-the-art methods that rely on optimization or sequential view synthesis, MD-ProjTex is computationally more efficient and achieves better quantitative and qualitative results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02762 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection Yildirim, Ahmet Burak Aydogdu, Mustafa Utku Ceylan, Duygu Dundar, Aysegul Computer Vision and Pattern Recognition We introduce MD-ProjTex, a method for fast and consistent text-guided texture generation for 3D shapes using pretrained text-to-image diffusion models. At the core of our approach is a multi-view consistency mechanism in UV space, which ensures coherent textures across different viewpoints. Specifically, MD-ProjTex fuses noise predictions from multiple views at each diffusion step and jointly updates the per-view denoising directions to maintain 3D consistency. In contrast to existing state-of-the-art methods that rely on optimization or sequential view synthesis, MD-ProjTex is computationally more efficient and achieves better quantitative and qualitative results. |
| title | MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.02762 |