State of the art on 3D reconstruction with RGB‐D cameras

M Zollhöfer, P Stotko, A Görlitz… - Computer graphics …, 2018 - Wiley Online Library
The advent of affordable consumer grade RGB‐D cameras has brought about a profound
advancement of visual scene reconstruction methods. Both computer graphics and …

Playing for data: Ground truth from computer games

SR Richter, V Vineet, S Roth, V Koltun - … 11-14, 2016, Proceedings, Part II …, 2016 - Springer
Recent progress in computer vision has been driven by high-capacity models trained on
large datasets. Unfortunately, creating large datasets with pixel-level labels has been …

Pix2vox: Context-aware 3d reconstruction from single and multi-view images

H Xie, H Yao, X Sun, S Zhou… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Recovering the 3D representation of an object from single-view or multi-view RGB images
by deep neural networks has attracted increasing attention in the past few years. Several …

Pix2Vox++: Multi-scale context-aware 3D object reconstruction from single and multiple images

H Xie, H Yao, S Zhang, S Zhou, W Sun - International Journal of Computer …, 2020 - Springer
Recovering the 3D shape of an object from single or multiple images with deep neural
networks has been attracting increasing attention in the past few years. Mainstream works …

A benchmark dataset and evaluation for non-lambertian and uncalibrated photometric stereo

B Shi, Z Wu, Z Mo, D Duan… - Proceedings of the …, 2016 - openaccess.thecvf.com
Recent progress on photometric stereo extends the technique to deal with general materials
and unknown illumination conditions. However, due to the lack of suitable benchmark data …

Lego: Learning edge with geometry all at once by watching videos

Z Yang, P Wang, Y Wang, W Xu… - Proceedings of the …, 2018 - openaccess.thecvf.com
Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep
convolutional network is attracting significant attention. In this paper, we introduce a “3D as …

Matryoshka networks: Predicting 3d geometry via nested shape layers

SR Richter, S Roth - … of the IEEE conference on computer …, 2018 - openaccess.thecvf.com
In this paper, we develop novel, efficient 2D encodings for 3D geometry, which enable
reconstructing full 3D shapes from a single image at high resolution. The key idea is to pose …

Uni-3d: A universal model for panoptic 3d scene reconstruction

X Zhang, Z Chen, F Wei, Z Tu - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Performing holistic 3D scene understanding from a single-view observation, involving
generating instance shapes and 3D scene segmentation, is a long-standing challenge …

Sail-vos: Semantic amodal instance level video object segmentation-a synthetic dataset and baselines

YT Hu, HS Chen, K Hui, JB Huang… - Proceedings of the …, 2019 - openaccess.thecvf.com
Abstract We introduce SAIL-VOS (Semantic Amodal Instance Level Video Object
Segmentation), a new dataset aiming to stimulate semantic amodal segmentation research …

Domain stylization: A strong, simple baseline for synthetic to real image domain adaptation

A Dundar, MY Liu, TC Wang, J Zedlewski… - arXiv preprint arXiv …, 2018 - arxiv.org
Deep neural networks have largely failed to effectively utilize synthetic data when applied to
real images due to the covariate shift problem. In this paper, we show that by applying a …