paper-with-me

홈 › Papers

LLM-Guided Material Inference for 3D Point Clouds

2025-12-02 · Nafiseh Izadyar, Teseo Schneider arxiv

Most existing 3D shape datasets and models focus solely on geometry, overlooking the material properties that determine how objects appear. We introduce a two-stage large language model (LLM) based method for inferring material composition directly from 3D point clouds with coarse segmentations. Our key insight is to decouple reasoning about what an object is from what it is made of. In the first stage, an LLM predicts the object's semantic; in the second stage, it assigns plausible materials to each geometric segment, conditioned on the inferred semantics. Both stages operate in a zero-shot manner, without task-specific training. Because existing datasets lack reliable material annotations, we evaluate our method using an LLM-as-a-Judge implemented in DeepEval. Across 1,000 shapes from Fusion/ABS and ShapeNet, our method achieves high semantic and material plausibility. These results demonstrate that language models can serve as general-purpose priors for bridging geometric reasoning and material understanding in 3D data.

📄 PDF Abstract BibTeX arXiv:2512.03237

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

DexDiffuser: Generating Dexterous Grasps with Diffusion Models

2024-02-05 · Zehang Weng, Haofei Lu, Danica Kragic, Jens Lundell

We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and …

DenoisingGrasp GenerationObject

GA-VINO: A Geometry-Aware Variational Physics-informed Neural Operator for Mindlin-Reissner Plates

2026-06-15 · Siqi Wang, Daobo Sun, Yizheng Wang, Yilong Zhang 외 arxiv

Plate and shell structures are widely used in engineering fields. Rapid response prediction for such structures under complex geometries, heterogeneous materials, and varying loads is important for engineering design, bu…

Point Clouds

Simultaneous Monitoring of Shape and Surface Color via 4D Point Clouds: A Registration-free Approach

2026-05-09 · Mariafrancesca Patalano, Giovanna Capizzi, Kamran Paynabar arxiv

Advanced manufacturing technologies allow for the production of intricate parts featuring high shape complexity and spatially-varying material composition. Data fusion of point clouds with chromatic attributes provides 4…

Point Clouds

Neighborhood Spatial Aggregation MC Dropout for Efficient Uncertainty-aware Semantic Segmentation in Point Clouds

2021-12-05 · Chao Qi, Jianqin Yin

Uncertainty-aware semantic segmentation of the point clouds includes the predictive uncertainty estimation and the uncertainty-guided model optimization. One key challenge in the task is the efficiency of point-wise pred…

Model OptimizationSemantic Segmentation

Label-Guided Auxiliary Training Improves 3D Object Detector

2022-07-24 · Yaomin Huang, Xinmei Liu, Yichen Zhu, Zhiyuan Xu 외

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3…

3D Object DetectionObjectobject-detectionObject Detection