We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.

The method begins with an iterative Gaussian cloud soft clustering module, offering structured temporal point cloud representations.

We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas.

A novel global optimization framework is also proposed to improve the system accuracy like traditional bundle adjustment.

Systems of interacting objects often evolve under the influence of field effects that govern their dynamics, yet previous works have abstracted away from such effects, and assume that systems evolve in a vacuum. In this work, we focus on discovering these fields, and infer them from the observed dynamics alone, without directly observing them.

In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation.

In this work, we propose a new representation for molecules that overcomes those limitations.