Completing point cloud from few points by Wasserstein GAN and Transformers
This addresses a challenge in vision and robotics applications where captured objects have sparse point data, though it appears incremental as it adapts existing techniques to a specific bottleneck.
The paper tackles the problem of completing 3D objects from very few point cloud inputs, where existing methods fail, by introducing a Wasserstein GAN and Transformer-based approach. Experimental results on ShapeNet show improved performance for many points and stable completion for few points.
In many vision and robotics applications, it is common that the captured objects are represented by very few points. Most of the existing completion methods are designed for partial point clouds with many points, and they perform poorly or even fail completely in the case of few points. However, due to the lack of detail information, completing objects from few points faces a huge challenge. Inspired by the successful applications of GAN and Transformers in the image-based vision task, we introduce GAN and Transformer techniques to address the above problem. Firstly, the end-to-end encoder-decoder network with Transformers and the Wasserstein GAN with Transformer are pre-trained, and then the overall network is fine-tuned. Experimental results on the ShapeNet dataset show that our method can not only improve the completion performance for many input points, but also keep stable for few input points. Our source code is available at https://github.com/WxfQjh/Stability-point-recovery.git.