Make3D: Learning 3D Scene Structure from a Single Still Image

By Ashutosh Saxena, Min Sun, Andrew Y. Ng. 2009

1,623 citations recorded by the source corpus.

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

Citations in the corpus

A Point Set Generation Network for 3D Object Reconstruction from a Single Image (2016, background): “[11, 18] pioneered the use of learning-based approach for simple geometric structures.”
Synthetic Data for Text Localisation in Natural Images (2016, methodology): “We prefer to estimate an imperfect depth map instead because: (1) it allows essentially any scene type background image to be used, instead of only the ones for which RGBD data are available, and (2) because publicly available RGBD datasets such as NYUDv2 [40], B3DO [22], Sintel [4], and Make3D [38]”
Kernel Belief Propagation (2011, methodology): “We used a set of 274 images taken on the Stanford campus, including both indoor and outdoor scenes (Saxena et al., 2009).”
Learning human activities and object affordances from RGB-D videos (2012, methodology): “MRFs are a workhorse of machine learning, and have been successfully applied to many applications (e.g. Saxena et al., 2009).”
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (2018, background): “Early works can be traced back to Hoiem et al. [14] and Saxena et al. [25].”
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (2018, background): “Other representations aim to use orientation [36], rotational invariance [15] or 3D-SURF features [16].”
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017, background): “In the ﬁeld of computer vision, there have also been abundant works exploiting the idea for reconstruction 3D shapes of faces [Kemelmacher-Shlizerman and Basri, 2011], objects [Tappen et al., 2003], and scenes [Hoiem et al., 2005, Saxena et al., 2009].”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, methodology): “Inspired by early works that used machine learning to learn a 2D-to-3D mapping for scene understanding [29,30], data driven approaches have been recently proposed to solve the daunting problem of recovering the shape of an object from just a single image [31,32] for a given number of object…”
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2017, methodology): “We demonstrate the efﬁcacy of our method for regression using two popular monocular depth regression datasets, Make3D [25] and NYUv2 Depth [23].”
Deep convolutional neural fields for depth estimation from a single image (2014, methodology): “As can be observed, our method outperforms classic methods like Make3d [15], DepthTransfer [5] with large margins.”
Accurate Uncertainties for Deep Learning Using Calibrated Regression (2018, methodology): “We also perform depth estimation on the larger Make3D dataset (Saxena et al., 2009), using the setup of Kendall and Gal (2017).”
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields (2015, methodology): “In the following, we give a brief introduction to the most closely related work.”
Deep Stereo: Learning to Predict New Views from the World's Imagery (2015, methodology): “Automatic single-view methods include the Make3D system of Saxena et al. [26], which uses aligned photos and laser scans as training data, and the automatic photo pop-up work of Hoiem et al. [14], which uses images with manually annotated geometric classes.”
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer (2019, background): “based formulations [3], simple geometric assumptions [2],”
Deeper Depth Prediction with Fully Convolutional Residual Networks (2016, methodology): “Their work has been later extended to 3D scene reconstruction [30].”
BA-Net: Dense Bundle Adjustment Network (2018, methodology): “Before the raise of deep learning based methods, some works predict depth from a single image based on MRF [40, 41], semantic segmentation [31], or manually designed features [25].”
PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing (2018, methodology): “On the depth estimation task, we compare with several state-of-the-art methods, including: methods adopting hand-crafted features and deep representations [46, 46, 20, 27, 10, 9, 29, 28], and methods considering graphical modeling with CNN [33, 32, 61, 51, 54].”