5 papers
FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand
Dominic Maggio, Nicolas Gorlo, Kris Hauser +1
We present the first approach to build hierarchical task-driven 3D scene graphs of arbitrary indoor or outdoor environments using an uncalibrated monocular camera in real-time. We…
Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization
Wei-Cheng Huang, Jiaheng Han, Xiaohan Ye +2
Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in cluttered en…
Map Space Belief Prediction for Manipulation-Enhanced Mapping
Joao Marcos Correia Marques, Nils Dengler, Tobias Zaenker +4
Searching for objects in cluttered environments requires selecting efficient viewpoints and manipulation actions to remove occlusions and reduce uncertainty in object locations, sh…
Safe Leaf Manipulation for Accurate Shape and Pose Estimation of Occluded Fruits
Shaoxiong Yao, Sicong Pan, Maren Bennewitz +1
Fruit monitoring plays an important role in crop management, and rising global fruit consumption combined with labor shortages necessitates automated monitoring with robots. Howeve…
On the Overconfidence Problem in Semantic 3D Mapping
Joao Marcos Correia Marques, Albert Zhai, Shenlong Wang +1
Semantic 3D mapping, the process of fusing depth and image segmentation information between multiple views to build 3D maps annotated with object classes in real-time, is a recent…