activity
20182022
most citedLION: Latent Point Diffusion Models for 3D Shape Generation

190 citations · 233 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2023

Neural Kernel Surface Reconstruction

Jiahui Huang, Zan Gojcic, Matan Atzmon +3

We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel…

cs.CV2023

Neural LiDAR Fields for Novel View Synthesis

Shengyu Huang, Zan Gojcic, Zian Wang +5

We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from…

cs.CV2022190 cited

LION: Latent Point Diffusion Models for 3D Shape Generation

Xiaohui Zeng, Arash Vahdat, Francis Williams +4

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 generat…

cs.CV20227 cited

Learning Smooth Neural Functions via Lipschitz Regularization

Hsueh-Ti Derek Liu, Francis Williams, Alec Jacobson +2

Neural implicit fields have recently emerged as a useful representation for 3D shapes. These fields are commonly represented as neural networks which map latent descriptors and 3D…

cs.CV2020

Human 3D keypoints via spatial uncertainty modeling

Francis Williams, Or Litany, Avneesh Sud +2

We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint. Our technique employs a principled approach to model…

cs.CV2019

VoronoiNet: General Functional Approximators with Local Support

Francis Williams, Daniele Panozzo, Kwang Moo Yi +1

Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it -- via a novel…