Abo: Dataset and benchmarks for real-world 3d object understanding

J Collins, S Goel, K Deng, A Luthra… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed
to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog …

Image-based 3D object reconstruction: State-of-the-art and trends in the deep learning era

XF Han, H Laga, M Bennamoun - IEEE transactions on pattern …, 2019 - ieeexplore.ieee.org
3D reconstruction is a longstanding ill-posed problem, which has been explored for decades
by the computer vision, computer graphics, and machine learning communities. Since 2015 …

What do single-view 3d reconstruction networks learn?

M Tatarchenko, SR Richter, R Ranftl… - Proceedings of the …, 2019 - openaccess.thecvf.com
Convolutional networks for single-view object reconstruction have shown impressive
performance and have become a popular subject of research. All existing techniques are …

Deep learning methods for calibrated photometric stereo and beyond: A survey

Y Ju, KM Lam, W Xie, H Zhou, J Dong, B Shi - arXiv preprint arXiv …, 2022 - arxiv.org
Photometric stereo recovers the surface normals of an object from multiple images with
varying shading cues, ie, modeling the relationship between surface orientation and …

Deep Learning Methods for Calibrated Photometric Stereo and Beyond

Y Ju, KM Lam, W Xie, H Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Photometric stereo recovers the surface normals of an object from multiple images with
varying shading cues, ie, modeling the relationship between surface orientation and …

Normattention-psn: A high-frequency region enhanced photometric stereo network with normalized attention

Y Ju, B Shi, M Jian, L Qi, J Dong, KM Lam - International Journal of …, 2022 - Springer
Photometric stereo aims to recover the surface normals of a 3D object from various shading
cues, establishing the relationship between two-dimensional images and the object …

Self-supervised single-view 3d reconstruction via semantic consistency

X Li, S Liu, K Kim, S De Mello, V Jampani… - Computer Vision–ECCV …, 2020 - Springer
We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh
shape, texture and camera pose of a target object with a collection of 2D images and …

Estimating high-resolution surface normals via low-resolution photometric stereo images

Y Ju, M Jian, C Wang, C Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Acquiring high-resolution 3D surface structures is a crucial task in computer vision as it
provides more detailed surface textures and clearer structures. Photometric stereo can …

Fig-nerf: Figure-ground neural radiance fields for 3d object category modelling

C Xie, K Park, R Martin-Brualla… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object
category models from collections of input images. In contrast to previous work, we are able …

Shelf-supervised mesh prediction in the wild

Y Ye, S Tulsiani, A Gupta - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
We aim to infer 3D shape and pose of objects from a single image and propose a learning-
based approach that can train from unstructured image collections, using only segmentation …