Unsupervised 2D-3D lifting of non-rigid objects using local constraints
This work addresses the challenge of 3D reconstruction for non-rigid objects, which is important for computer vision applications, but it is incremental as it builds on existing low-rank constraint methods by localizing them.
The paper tackles the ill-posed problem of predicting 3D shapes from 2D keypoints for non-rigid objects by using generic high-capacity models with unsupervised loss and localized low-rank constraints, reducing state-of-the-art reconstruction error on the S-Up3D dataset by over 70%.
For non-rigid objects, predicting the 3D shape from 2D keypoint observations is ill-posed due to occlusions, and the need to disentangle changes in viewpoint and changes in shape. This challenge has often been addressed by embedding low-rank constraints into specialized models. These models can be hard to train, as they depend on finding a canonical way of aligning observations, before they can learn detailed geometry. These constraints have limited the reconstruction quality. We show that generic, high capacity models, trained with an unsupervised loss, allow for more accurate predicted shapes. In particular, applying low-rank constraints to localized subsets of the full shape allows the high capacity to be suitably constrained. We reduce the state-of-the-art reconstruction error on the S-Up3D dataset by over 70%.