Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

Abstract Recent Diffusion Transformers (ie, DiT) have demonstrated their powerful
effectiveness in generating high-quality 2D images. However, it is unclear how the …

We propose a 3D shape generation framework (SDF-Diffusion in short) that uses denoising
diffusion models with continuous 3D representation via signed distance fields (SDF). Unlike …

Detecting anomalous samples in set data is a problem attracting increased interest due to
novel modalities, such as point-cloud data produced by lidars. Novel methods including …

Autonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR
sensors presents a significant scaling-up challenge. While recent efforts have explored deep …

Diffusion models have emerged as a powerful tool for point cloud generation. A key
component that drives the impressive performance for generating high-quality samples from …

Diffusion models generating images conditionally on text, such as Dall-E 2 and Stable
Diffusion, have recently made a splash far beyond the computer vision community. Here, we …

Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable
models with remarkable sample generation quality and training stability. These properties …

Abstract We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and
3D data for weakly supervised point cloud segmentation. Research studies have shown that …

Simulating showers of particles in highly-granular detectors is a key frontier in the
application of machine learning to particle physics. Achieving high accuracy and speed with …