Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
–Neural Information Processing Systems
However, they often fail to produce realistic geometric details, resulting in overly smooth surfaces or geometric details inaccurately baked in albedo maps. To address this, we introduce a new method that incorporates touch as an additional modality to improve the geometric details of generated 3D assets. We design a lightweight 3D texture field to synthesize visual and tactile textures, guided by 2D diffusion model priors on both visual and tactile domains. We condition the visual texture generation on high-resolution tactile normals and guide the patch-based tactile texture refinement with a customized TextureDreambooth. We further present a multi-part generation pipeline that enables us to synthesize different textures across various regions.
Neural Information Processing Systems
May-26-2025, 21:01:40 GMT
- Technology:
- Information Technology > Artificial Intelligence
- Robots > Manipulation (0.45)
- Machine Learning (0.43)
- Information Technology > Artificial Intelligence