activity
20182022
most citedDRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images

17 citations · 80 across the 15 of their papers we have counts for

collaborators

29 papers

cs.CV20221 cited

NeAF: Learning Neural Angle Fields for Point Normal Estimation

Shujuan Li, Junsheng Zhou, Baorui Ma +2

Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors o…

cs.CV202216 cited

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

Qing Li, Yu-Shen Liu, Jin-San Cheng +3

We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations. Previous methods focus on le…

cs.CV20225 cited

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Baorui Ma, Yu-Shen Liu, Matthias Zwicker +1

Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented…

cs.CV2022

Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

Baorui Ma, Yu-Shen Liu, Zhizhong Han

It is an important task to reconstruct surfaces from 3D point clouds. Current methods are able to reconstruct surfaces by learning Signed Distance Functions (SDFs) from single poin…

cs.CV20223 cited

Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds

Tianyang Li, Xin Wen, Yu-Shen Liu +2

Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes,…

cs.CV20221 cited

3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow

Xin Wen, Junsheng Zhou, Yu-Shen Liu +2

Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image. So far, mos…