Taming Transformers for Realistic Lidar Point Cloud Generation

arXiv:2404.05505v1 Announce Type: cross
Abstract: Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling. However, DMs often fail to realistically model Lidar raydrop noise due to their inherent denoising process. To retain the strength of iterative sampling while enhancing the generation of raydrop noise, we introduce LidarGRIT, a generative model that uses auto-regressive transformers to iteratively sample the range images in the latent space …

arxiv cloud cs.cv cs.lg cs.ro lidar transformers type