CVPR 2024: Robust Depth Enhancement via Polarization Prompt Fusion Tuning

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

[CVPR 2020] Normal Assisted Stereo Depth Estimation

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

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.

Reconstruct mesh from point cloud data generated by 3D scanner

nyuv2 toolbox for data extraction and loading.

DIODE Development Toolkit

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

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

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

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

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

Normal estimation based on dual camera input

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

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

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

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

MSCV 2019 Capstone Project