Single-View 3D Reconstruction

38 papers with code • 6 benchmarks • 12 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Learning Implicit Fields for Generative Shape Modeling

czq142857/implicit-decoder CVPR 2019

We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes.

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

laughtervv/DISN NeurIPS 2019

Reconstructing 3D shapes from single-view images has been a long-standing research problem.

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

ChrisWu1997/PQ-NET CVPR 2020

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly.

Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning

ShichenLiu/SoftRas ICCV 2019

Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation.

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction

zhou13/symmetrynet 17 Jun 2020

In this work, we focus on object-level 3D reconstruction and present a geometry-based end-to-end deep learning framework that first detects the mirror plane of reflection symmetry that commonly exists in man-made objects and then predicts depth maps by finding the intra-image pixel-wise correspondence of the symmetry.

Learning Single-View 3D Reconstruction with Limited Pose Supervision

stevenygd/3d-recon ECCV 2018

It is expensive to label images with 3D structure or precise camera pose.

Domain-Adaptive Single-View 3D Reconstruction

Gitikameher/Domain-Adaptive-Single-View-3D-Reconstruction ICCV 2019

In this paper, we propose a framework to improve over these challenges using adversarial training.

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

nv-tlabs/DIB-R NeurIPS 2019

Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering.

Hyperparameter-Free Losses for Model-Based Monocular Reconstruction

hyperparams-free/hyperparams-free-3D-losses 16 Aug 2019

This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM).