TouchDream：通过想象触觉实现三维物体补全
TouchDream: 3D Object Completion through Imagined Touch
把触觉传感当作可生成的模态：以粗点云和采样接触位姿为条件，用扩散模型生成紧凑的触觉潜变量，再将其反投影到 3D 空间来优化几何，为点云补全提供了一条不依赖视觉线索、可复用的细节引导思路。
原文依据 generate compact tactile latent representations conditioned on coarse points and sampled touch poses
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论点云补全对鲁棒的三维感知至关重要，但仍具挑战性。由粗到细的方法在缺少关键结构时会导致无约束的局部猜测，而基于扩散模型的方法可能引入几何不一致。为克服这些局限，我们提出 TouchDream，一个新框架，利用扩散模型在物体表面“想象”触觉传感，从而将传感过程重新表述为可学习的生成建模任务。与视觉线索不同，触觉数据提供丰富的局部几何，可直接转换到三维空间进行点融合，为细节感知的补全提供有力引导。具体而言，我们的方法以粗点云和采样的接触位姿为条件，生成紧凑的触觉潜变量表示。这些生成的触觉随后被用于优化粗几何。大量实验表明，我们的 TouchDream 模型达到了最优性能。
英文原文摘要 967 字符
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.