3D Reconstruction

307 papers with code • 8 benchmarks • 30 datasets

Image: Gwak et al

Libraries

Use these libraries to find 3D Reconstruction models and implementations

Most implemented papers

Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

MIT-SPARK/Kimera 6 Oct 2019

We provide an open-source C++ library for real-time metric-semantic visual-inertial Simultaneous Localization And Mapping (SLAM).

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

chrischoy/3D-R2N2 2 Apr 2016

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2).

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

nvlabs/instant-ngp 16 Jan 2022

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.

The Double Sphere Camera Model

ethz-asl/kalibr 24 Jul 2018

We evaluate the model using a calibration dataset with several different lenses and compare the models using the metrics that are relevant for Visual Odometry, i. e., reprojection error, as well as computation time for projection and unprojection functions and their Jacobians.

Occupancy Networks: Learning 3D Reconstruction in Function Space

LMescheder/Occupancy-Networks CVPR 2019

With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity.

MVSNet: Depth Inference for Unstructured Multi-view Stereo

YoYo000/MVSNet ECCV 2018

We present an end-to-end deep learning architecture for depth map inference from multi-view images.

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Facebookresearch/deepsdf CVPR 2019

In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.

Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images

hzxie/Pix2Vox ICCV 2019

Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e. g., table legs) from different coarse 3D volumes to obtain a fused 3D volume.

PCRNet: Point Cloud Registration Network using PointNet Encoding

vinits5/learning3d 21 Aug 2019

PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion.

A Point Set Generation Network for 3D Object Reconstruction from a Single Image

fanhqme/PointSetGeneration CVPR 2017

Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.