Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations
This addresses the challenge of reducing data annotation costs for 3D articulated object modeling, though it is incremental as it builds on existing neural representation methods.
The paper tackles the problem of learning 3D geometry-aware representations of articulated objects without requiring expensive ground truth data like image-pose pairs or foreground masks, achieving this through an unsupervised GAN-based method that enables controllable 3D rendering with random poses.
We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects, in which no image-pose pairs or foreground masks are used for training. Though photorealistic images of articulated objects can be rendered with explicit pose control through existing 3D neural representations, these methods require ground truth 3D pose and foreground masks for training, which are expensive to obtain. We obviate this need by learning the representations with GAN training. The generator is trained to produce realistic images of articulated objects from random poses and latent vectors by adversarial training. To avoid a high computational cost for GAN training, we propose an efficient neural representation for articulated objects based on tri-planes and then present a GAN-based framework for its unsupervised training. Experiments demonstrate the efficiency of our method and show that GAN-based training enables the learning of controllable 3D representations without paired supervision.