4 papers · 1 filter
From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
Joy Hsu, Emily Jin, Jiajun Wu +1
Real-world scenes, such as those in ScanNet, are difficult to capture, with highly limited data available. Generating realistic scenes with varied object poses remains an open and…
Predicate Hierarchies Improve Few-Shot State Classification
Emily Jin, Joy Hsu, Jiajun Wu
State classification of objects and their relations is core to many long-horizon tasks, particularly in robot planning and manipulation. However, the combinatorial explosion of pos…
What Makes a Maze Look Like a Maze?
Joy Hsu, Jiayuan Mao, Joshua B. Tenenbaum +2
A unique aspect of human visual understanding is the ability to flexibly interpret abstract concepts: acquiring lifted rules explaining what they symbolize, grounding them across f…
Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners
Chun Feng, Joy Hsu, Weiyu Liu +1
3D visual grounding is a challenging task that often requires direct and dense supervision, notably the semantic label for each object in the scene. In this paper, we instead study…