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 rather
than image space. Furthermore, LidarGRIT utilises VQ-VAE to separately decode
range images and raydrop masks. Our results show that LidarGRIT achieves
superior performance compared to SOTA models on KITTI-360 and KITTI odometry
datasets. Code available at:this https URL

LidarGRIT 利用自回归变换器在潜在空间而不是图像空间中迭代采样范围图像，利用 VQ-VAE 分别解码范围图像和射线丢失遮罩，取得了 KITTI-360 和 KITTI odometry 数据集上 SOTA 模型无法比拟的卓越性能。

驯服 Transformer 以实现真实 Lidar 点云生成

Taming Transformers for Realistic Lidar Point Cloud Generation

This paper presents a novel generative model for Computer Aided Design (CAD)
that 1) represents high-level design concepts of a CAD model as a three-level
hierarchical tree of neural codes, from global part arrangement down to local
curve geometry; and 2) controls the generation or completion of CAD models by
specifying the target design using a code tree. Concretely, a novel variant of
a vector quantized VAE with "masked skip connection" extracts design variations
as neural codebooks at three levels. Two-stage cascaded auto-regressive
transformers learn to generate code trees from incomplete CAD models and then
complete CAD models following the intended design. Extensive experiments
demonstrate superior performance on conventional tasks such as random
generation while enabling novel interaction capabilities on conditional
generation tasks. The code is available at
this https URL

本文提出了一种新颖的计算机辅助设计 (CAD) 的生成模型，通过使用神经编码的三级分层树来表示 CAD 模型的高级设计概念，并且指定目标设计，从而控制 CAD 模型的生成或完成。