Spatio-temporal self-supervised representation learning for 3d point clouds
To date, various 3D scene understanding tasks still lack practical and generalizable pre-
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …
Foldingnet: Point cloud auto-encoder via deep grid deformation
Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised learning tasks on point clouds such as classification and …
state-of-the-art for supervised learning tasks on point clouds such as classification and …
Deep learning methods for Reynolds-averaged Navier–Stokes simulations of airfoil flows
This study investigates the accuracy of deep learning models for the inference of Reynolds-
averaged Navier–Stokes (RANS) solutions. This study focuses on a modernized U-net …
averaged Navier–Stokes (RANS) solutions. This study focuses on a modernized U-net …
Pu-net: Point cloud upsampling network
Learning and analyzing 3D point clouds with deep networks is challenging due to the
sparseness and irregularity of the data. In this paper, we present a data-driven point cloud …
sparseness and irregularity of the data. In this paper, we present a data-driven point cloud …
Sdfdiff: Differentiable rendering of signed distance fields for 3d shape optimization
We propose SDFDiff, a novel approach for image-based shape optimization using
differentiable rendering of 3D shapes represented by signed distance functions (SDFs) …
differentiable rendering of 3D shapes represented by signed distance functions (SDFs) …
Robustness of conditional gans to noisy labels
KK Thekumparampil, A Khetan… - Advances in neural …, 2018 - proceedings.neurips.cc
We study the problem of learning conditional generators from noisy labeled samples, where
the labels are corrupted by random noise. A standard training of conditional GANs will not …
the labels are corrupted by random noise. A standard training of conditional GANs will not …
Self-supervised deep learning on point clouds by reconstructing space
J Sauder, B Sievers - Advances in Neural Information …, 2019 - proceedings.neurips.cc
Point clouds provide a flexible and natural representation usable in countless applications
such as robotics or self-driving cars. Recently, deep neural networks operating on raw point …
such as robotics or self-driving cars. Recently, deep neural networks operating on raw point …
Rl-gan-net: A reinforcement learning agent controlled gan network for real-time point cloud shape completion
Abstract We present RL-GAN-Net, where a reinforcement learning (RL) agent provides fast
and robust control of a generative adversarial network (GAN). Our framework is applied to …
and robust control of a generative adversarial network (GAN). Our framework is applied to …
Deformable shape completion with graph convolutional autoencoders
The availability of affordable and portable depth sensors has made scanning objects and
people simpler than ever. However, dealing with occlusions and missing parts is still a …
people simpler than ever. However, dealing with occlusions and missing parts is still a …
Pointgrow: Autoregressively learned point cloud generation with self-attention
Generating 3D point clouds is challenging yet highly desired. This work presents a novel
autoregressive model, PointGrow, which can generate diverse and realistic point cloud …
autoregressive model, PointGrow, which can generate diverse and realistic point cloud …