TouchDream: 3D Object Completion through Imagined Touch
Yuanbo Wang, Xinning Wang, Zhaoxuan Zhang, Changlong Wang, Qianchen Xia, Xiaopeng Wei, Xin Yang
Abstract
Point cloud completion is crucial for robust 3D perception but remains challenging. Coarse-to-fine methods can lead to unconstrained local guesses in the absence of key structures, whereas diffusion-based approaches may introduce geometric inconsistencies. To overcome these limitations, we present TouchDream, a novel framework that leverages a diffusion model to `dream' of tactile sensing on object surfaces, which reformulates the sensing process as a learnable generative modeling task. Unlike visual cues, tactile data provides rich local geometry that can be directly converted into 3D space for point fusion, offering a powerful guide for detail-aware completion. Specifically, our approach generate compact tactile latent representations conditioned on coarse points and sampled touch poses. These generated touches are then used to optimize the coarse geometry. Extensive experiments show that our TouchDream model achieves the state-of-the-art performance.
BibTeX
@inproceedings{cvpr2026_touchdream3dobje,
title = {TouchDream: 3D Object Completion through Imagined Touch},
author = {Yuanbo Wang and Xinning Wang and Zhaoxuan Zhang and Changlong Wang and Qianchen Xia and Xiaopeng Wei and Xin Yang},
booktitle = {CVPR 2026},
year = {2026}
}