Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)

[CVPR 2020] Normal Assisted Stereo Depth Estimation

A novel fast approximate least squares normal estimator using the structural information of certain LiDAR, is fast and accurate compared to PCL, and meets the real-time requirements of the LIO system.

DIODE Development Toolkit

Facial Depth and Normal Estimation using Dual-Pixel Camera (ECCV 22)

nyuv2 toolbox for data extraction and loading.

Official GitHub repo for VecKM. A very efficient and descriptive local geometry encoder / point tokenizer / patch embedder. ICML2024.

CVPR 2024: Robust Depth Enhancement via Polarization Prompt Fusion Tuning

Reconstruct mesh from point cloud data generated by 3D scanner

(BMVC 2020 Oral) Neighbourhood-Insensitive Point Cloud Normal Estimation Network

Efficient Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction

Comparison of a few different methods for estimating surface normals in a point cloud.

MSCV 2019 Capstone Project

Code for our Building Facades to Normal Maps – Adversarial Learning from Single View Images work accepted at CRV 2021

tcensReg is a package written to obtain maximum likelihood estimates from a truncated normal distribution with censoring.

Normal estimation based on dual camera input