Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction

CVPR 2022

Yining Hong1 Kaichun Mo2 Li Yi3 Leonidas J. Guibas 2 Antonio Torralba5 Joshua B. Tenenbaum5 Chuang Gan4
1UCLA       2Stanford University       3Tsinghua University         4MIT-IBM Watson AI Lab       5MIT


This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to the physical interactions between the object and the user. Given a malfunctional object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. Inspired by this, we propose FixIt, a dataset that contains about 5k poorly-designed 3D physical objects paired with choices to fix them. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics. Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix. Experimental results show that our framework outperforms baseline models by a large margin, and can generalize well to objects with similar interaction types.



@inproceedings{hong2021fixing, author = {Hong, Yining and Mo, Kaichun and Yi, Li and Guibas, Leonidas J and Torralba, Antonio and Tenenbaum, Joshua B and Gan, Chuang}, title = {Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction}, booktitle = {CVPR}, year = {2022} }

Paper     Code     Data & Checkpoint