paper-with-me

Papers

Touch-GS: Visual-Tactile Supervised 3D Gaussian Splatting

2024-03-14 · Aiden Swann, Matthew Strong, Won Kyung Do, Gadiel Sznaier Camps, Mac Schwager, Monroe Kennedy III

In this work, we propose a novel method to supervise 3D Gaussian Splatting (3DGS) scenes using optical tactile sensors. Optical tactile sensors have become widespread in their use in robotics for manipulation and object representation; however, raw optical tactile sensor data is unsuitable to directly supervise a 3DGS scene. Our representation leverages a Gaussian Process Implicit Surface to implicitly represent the object, combining many touches into a unified representation with uncertainty. We merge this model with a monocular depth estimation network, which is aligned in a two stage process, coarsely aligning with a depth camera and then finely adjusting to match our touch data. For every training image, our method produces a corresponding fused depth and uncertainty map. Utilizing this additional information, we propose a new loss function, variance weighted depth supervised loss, for training the 3DGS scene model. We leverage the DenseTact optical tactile sensor and RealSense RGB-D camera to show that combining touch and vision in this manner leads to quantitatively and qualitatively better results than vision or touch alone in a few-view scene syntheses on opaque as well as on reflective and transparent objects. Please see our project page at http://armlabstanford.github.io/touch-gs

📄 PDF Abstract BibTeX arXiv:2403.09875

Code (0)

등록된 구현이 없습니다.

Tasks

3DGSDepth EstimationMonocular Depth EstimationTransparent objects

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces

2024-03-29 · Mauro Comi, Alessio Tonioni, Max Yang, Jonathan Tremblay 외

Touch and vision go hand in hand, mutually enhancing our ability to understand the world. From a research perspective, the problem of mixing touch and vision is underexplored and presents interesting challenges. To this …

3DGSNovel View SynthesisSurface Reconstruction

Touch and Go: Learning from Human-Collected Vision and Touch

2022-11-22 · Fengyu Yang, Chenyang Ma, Jiacheng Zhang, Jing Zhu 외

The ability to associate touch with sight is essential for tasks that require physically interacting with objects in the world. We propose a dataset with paired visual and tactile data called Touch and Go, in which human…

Image Stylization

Touch-R1: Reinforcing Touch Reasoning in MLLMs

2026-05-26 · Yingxin Lai, Yafei Zhou, Fucai Zhu, Siyu Zhu 외 arxiv

While rule-based reinforcement learning has recently catalyzed explicit reasoning in multimodal models, tactile reasoning remains largely underexplored. Existing tactile-language models primarily rely on supervised or co…

Reinforcement Learning

FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction

2024-10-10 · Irving Fang, Kairui Shi, Xujin He, Siqi Tan 외

Humans effortlessly integrate common-sense knowledge with sensory input from vision and touch to understand their surroundings. Emulating this capability, we introduce FusionSense, a novel 3D reconstruction framework tha…

3D ReconstructionCommon Sense ReasoningObject

RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data

2025-05-20 · Yoorhim Cho, Hongyeob Kim, Semin Kim, Youjia Zhang 외

Visuo-tactile perception aims to understand an object's tactile properties, such as texture, softness, and rigidity. However, the field remains underexplored because collecting tactile data is costly and labor-intensive.…

Retrieval