Abstract: We propose a novel point cloud U-Net diffusion architecture for 3-D generative modeling capable of generating high-quality and diverse 3-D shapes while maintaining fast generation times. Our ...
Abstract: The efficiency of neural network computations is heavily influenced by numerical precision management. Traditional floating-point (FP) representations offer high precision but are ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results