Data-Driven 3D Primitives for Single Image Understanding

By David F. Fouhey, Abhinav Kumar Gupta, Martial Hebert. 2013

201 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Geology, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Geology

In 3D Vision & Pose

Citations in the corpus

Unsupervised Visual Representation Learning by Context Prediction (2015, methodology): “r representation extract information that is useful for other, non-object-based tasks? To ﬁnd out, we ﬁne-tuned our network to perform the surface normal estimation on NYUv2 proposed in Fouhey et al. [19], following the ﬁnetuning procedure of Wang et al. [57] (hence, we compare directly to the unsup”
Scaling and Benchmarking Self-Supervised Visual Representation Learning (2019, methodology): “Setup: We use the surface normal estimation task [22], with the evaluation, and dataset splits as formulated in [5, 45, 68].”
Learning to See by Moving (2015, methodology): “For this purpose, we used image and odometry data recorded from a car moving through urban scenes, made available as part of the KITTI [15] and the San Francisco (SF) city [10] datasets.”
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture (2014, methodology): “match to discriminative local templates [10] followed by a global op-”
Cross-Stitch Networks for Multi-task Learning (2016, methodology): “We evaluate all our methods using the metrics from [18].”
Unsupervised Learning of Visual Representations Using Videos (2015, methodology): “For evaluation and generating the groundtruth, we adopt the protocols introduced in [12] which is used by different methods [12, 25, 13] on this task.”
Generative Image Modeling Using Style and Structure Adversarial Networks (2016, methodology): “In order to train our S(2)-GAN we combine adversarial loss with 3D surface normal prediction loss [39,40,41,42] to provide extra constraints during learning.”
Designing deep networks for surface normal estimation (2014, methodology): “We adopt the protocols introduced in [9] and used by state-of-the-art methods on this task [9, 10, 22].”
A Point Set Generation Network for 3D Object Reconstruction from a Single Image (2016, background): “As commodity 3D sensors become popular, RGBD database has been built and used to train learningbased systems [6, 8].”
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network (2014, background): “[2], and integrating them along with depth maps stands to improve overall performance [16].”
Transitive Invariance for Self-Supervised Visual Representation Learning (2017, methodology): “We follow the same protocols for generating surface normal ground truth and evaluations as [14, 28, 15].”
Matterport3D: Learning from RGB-D Data in Indoor Environments (2017, methodology): “These previous RGB-D datasets have been used to train models for several standard scene understanding tasks, including semantic segmentation [27, 33, 13, 40, 7], 3D object detection [31, 24, 14, 36, 37], normal estimation [41, 23, 9, 3], camera relocalization [30, 39], and others [47, 11, 12].”
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (2016, background): “surface normal and depth map) by reasoning about mid-level scene properties, such as discriminative 3D primitives [10], convex and concave edges [11], and style elements harvested by unsupervised learning [12].”
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation (2018, methodology): “Inspired from the geometry-based solution [9], we propose a novel neural network architecture, which takes initial surface normal and depth maps as input and predicts a better surface normal.”
Semi-global Stereo Matching with Surface Orientation Priors (2017, methodology): “, expected ground plane orientation in autonomous driving [28]), from semantic analysis [15, 16, 2], or from vanishing point analysis and Manhattan-world assumptions [41, 43, 17, 32, 36], which we also explore in this paper.”
What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction (2021, background): “5D properties [4] that are visible in the image, such as qualitative geometry [15, 24], depth [42] and normals [16].”
Deep Surface Normal Estimation With Hierarchical RGB-D Fusion (2019, methodology): “(a) RGB input; (b) depth input; normal estimation with (c) single RGB [33], (d) depth inpainting [9], (e) RGB-D early fusion [32], (f) proposed hierarchical RGB-D fusion.”
Single Image 3D without a Single 3D Image (2015, methodology): “We wish to show that unsupervised 3D learning can be effective for predicting 3D.”