This paper presents the first learning-based generative pipeline for effectively creating 3D
LEGO® 1 models. This task is very challenging due to the lack of dedicated representations …

Generating high-quality 3D assets from text and images has long been challenging,
primarily due to the absence of scalable 3D representations capable of capturing intricate …

We introduce Shape Tokens, a 3D representation that is continuous, compact, and easy to
incorporate into machine learning models. Shape Tokens act as conditioning vectors that …

Text-to-3D generation has achieved remarkable progress in recent years, yet evaluating
these methods remains challenging for two reasons: i) Existing benchmarks lack fine …

Large-scale 3D generative models require substantial computational resources yet often fall
short in capturing fine details and complex geometries at high resolutions. We attribute this …

Autoregressive (AR) models have achieved remarkable success in natural language and
image generation, but their application to 3D shape modeling remains largely unexplored …

In this paper, we introduce X-Ray, an innovative approach to 3D generation that employs a
new sequential representation, drawing inspiration from the depth-revealing capabilities of X …

One essential function of professional events, such as industry trade shows and academic
conferences, is to foster and extend a person's connections to others within the community of …