neureconMulti-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.
Stars: ✭ 697 (+657.61%)
Portrait FCN and 3D ReconstructionThis project is to convert PortraitFCN+ (by Xiaoyong Shen) from Matlab to Tensorflow, then refine the outputs from it (converted to a trimap) using KNN and ResNet, supervised by Richard Berwick.
Stars: ✭ 61 (-33.7%)
shape as points[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver
Stars: ✭ 398 (+332.61%)
simple-sfmA readable implementation of structure-from-motion
Stars: ✭ 19 (-79.35%)
ShapeFormerOfficial repository for the ShapeFormer Project
Stars: ✭ 97 (+5.43%)
FrameNetFrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
Stars: ✭ 115 (+25%)
pomdp-baselinesSimple (but often Strong) Baselines for POMDPs in PyTorch - ICML 2022
Stars: ✭ 162 (+76.09%)
PSVH-3d-reconstructionDeep Single-View 3D Object Reconstruction with Visual Hull Embedding
Stars: ✭ 38 (-58.7%)
LsmCode for Learnt Stereo Machines based on the NIPS 2017 paper
Stars: ✭ 233 (+153.26%)
retrieval-fuse[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"
Stars: ✭ 69 (-25%)
obman[cvpr19] Hands+Objects synthetic dataset, instructions to download and code to load the dataset
Stars: ✭ 120 (+30.43%)
MVSNet plMVSNet: Depth Inference for Unstructured Multi-view Stereo using pytorch-lightning
Stars: ✭ 49 (-46.74%)
PointCloudRegistrationToolAutomatically registers (aligns) and visualizes point clouds, or processes a whole bunch at once
Stars: ✭ 82 (-10.87%)
semantic-tsdfSemantic-TSDF for Self-driving Static Scene Reconstruction
Stars: ✭ 14 (-84.78%)
findpeaksThe detection of peaks and valleys in a 1d-vector or 2d-array (image)
Stars: ✭ 121 (+31.52%)
SpinNet[CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Stars: ✭ 181 (+96.74%)
SSVIOGraduation Project: A point cloud semantic segmentation and VIO based 3D reconstruction method using RGB-D and IMU
Stars: ✭ 25 (-72.83%)
Dicom-ViewerAn application displaying 2D/3D Dicom
Stars: ✭ 37 (-59.78%)
maksMotion Averaging
Stars: ✭ 52 (-43.48%)
StructuredLightCreating a 3D reconstruction of an object using multiple images
Stars: ✭ 42 (-54.35%)
sfm-disambiguation-colmapMaking Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures
Stars: ✭ 189 (+105.43%)
Point2MeshMeshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV2020)
Stars: ✭ 61 (-33.7%)
Structured3d[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
Stars: ✭ 224 (+143.48%)
over-parametrizationComputing various norms/measures on over-parametrized neural networks
Stars: ✭ 46 (-50%)
void-datasetVisual Odometry with Inertial and Depth (VOID) dataset
Stars: ✭ 74 (-19.57%)
Generalizing-Lottery-TicketsThis repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"
Stars: ✭ 48 (-47.83%)
NeuralPullImplementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
Stars: ✭ 149 (+61.96%)
PaiConvMeshOfficial repository for the paper "Learning Local Neighboring Structure for Robust 3D Shape Representation"
Stars: ✭ 19 (-79.35%)
mvsnerf[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.
Stars: ✭ 533 (+479.35%)
LPDC-NetCVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"
Stars: ✭ 27 (-70.65%)
3D-Public-Transport-SimulatorThe 3D Public Transport Simulator is a Unity-based simulation, which uses OpenStreetMap data in order to support the simulation of worldwide locations. The development was part of a Bachelor thesis.
Stars: ✭ 87 (-5.43%)
relative poseA Collection of Algorithms for Relative Pose Estimation of a Calibrated Camera
Stars: ✭ 27 (-70.65%)
RfDNetImplementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
Stars: ✭ 150 (+63.04%)
DSP-SLAM[3DV 2021] DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
Stars: ✭ 377 (+309.78%)
cv-arxiv-daily🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Stars: ✭ 216 (+134.78%)
r3liveA Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
Stars: ✭ 1,355 (+1372.83%)
ICONICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+596.74%)
global l0Global L0 algorithm for regularity-constrained plane fitting
Stars: ✭ 45 (-51.09%)
transformer generalizationThe official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
Stars: ✭ 58 (-36.96%)
pgdlWinning Solution of the NeurIPS 2020 Competition on Predicting Generalization in Deep Learning
Stars: ✭ 36 (-60.87%)
pyRANSAC-3DA python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm
Stars: ✭ 253 (+175%)
aistplusplus apiAPI to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset
Stars: ✭ 277 (+201.09%)
modulesThe official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.
Stars: ✭ 25 (-72.83%)
Genre ShapehdCode and Data Release for GenRe (NeurIPS 2018) and ShapeHD (ECCV 2018)
Stars: ✭ 241 (+161.96%)
PcnCode for PCN: Point Completion Network in 3DV'18 (Oral)
Stars: ✭ 238 (+158.7%)
softpoolSoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification - ECCV 2020 oral
Stars: ✭ 62 (-32.61%)
DmifNetThis repository contains the source codes for the paper "DmifNet: 3D Shape Reconstruction based on Dynamic Multi–Branch Information Fusion (ICPR 2020 Oral)"
Stars: ✭ 20 (-78.26%)
Face-XDemonstration of different algorithms and operations on faces. Join the Discord channel for discussion.
Stars: ✭ 226 (+145.65%)
extrapolategeneralize counter-examples of property-based testing
Stars: ✭ 13 (-85.87%)
3d-reconImplementation for paper "Learning Single-View 3D Reconstruction with Limited Pose Supervision".
Stars: ✭ 59 (-35.87%)
platonicganEscaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]
Stars: ✭ 40 (-56.52%)