Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction
This work solves the challenge of accurate 3D shape reconstruction from limited single images, which is important for applications in robotics and computer vision, though it is incremental as it builds on existing mixup techniques.
The paper tackles the problem of few-shot single-view 3D reconstruction by proposing Pose Adaptive Dual Mixup (PADMix), which addresses inconsistencies in shape predictions through a two-stage mixup procedure and pose adaptive learning, resulting in significant performance improvements over previous methods on ShapeNet and new benchmarks on Pix3D.
We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding. The stagewise training allows us to build upon the pose invariant representations to perform a follow-up latent mixup under one-to-one correspondences between features and ground-truth volumes. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.