Estimating image depth using shape collections

By Hao Su, Qi-Xing Huang, Niloy J. Mitra, Yangyan Li, Leonidas J. Guibas. 2014

98 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, 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 Media Technology

In 3D Vision & Pose

Citations in the corpus

A Point Set Generation Network for 3D Object Reconstruction from a Single Image (2016, background): “For example, [19, 13] proposed to deform and reassemble existing shapes into a new model to fit the observed image.”
RealPoint3D: Point Cloud Generation from a Single Image with Complex Background (2018, background): “In (Su et al. 2014) and (Huang, Wang, and Koltun 2015), the authors reconstructed the depth of objects from web-site collected images by exploiting a collection of aligned 3D models of related objects shape.”
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (2018, background): “[15] and Su et al.[29] retrieve shape components from a large dataset, assemble them and deform the assembled shape to fit the observed image.”
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 [44, 29], data driven approaches have been recently proposed to solve the daunting problem of recovering the shape of an object from just a single image [50, 30, 20, 47] for a given number of objec”
Single Image 3D Interpreter Network (2016, methodology): “Depth-/mesh-based models can recover detailed 3D object structure from a single image, either by adapting existing 3D models from a database [3,19,6,8,20,21,22,23,24], or by inferring from its detected 2D silhouette [5,7,4].”
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields (2015, background): “In the following, we give a brief introduction to the most closely related work.”
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (2016, background): “Recent work include instance detection of a small set of IKEA objects via contour-based alignment [26], depth prediction by aligning to renders of 3D shapes via hand-crafted features [44], object class detection via exemplar matching with mid-level elements [1, 7], and alignment via composition from”
Learning Dense Correspondence via 3D-Guided Cycle Consistency (2016, background): “Other works [17, 34] leverage image and shape collections for joint pose estimation and refining image-shape alignment, which are further applied to single-view object reconstruction and depth estimation.”
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views (2015, methodology): “Despite recent progress on 2D-3D matching and retrieval [27, 35, 48], detection by 2D-3D alignment lags behind state-of-the-art object detection systems based on annotated images, e.”
Joint embeddings of shapes and images via CNN image purification (2015, methodology): “The unified space also supports various other applications that require 3D representations of objects observed in images [Xu et al. 2011; Zheng et al. 2012; Su et al. 2014; Kholgade et al. 2014; Lee et al. 2015; Huang et al. 2015].”
ObjectNet3D: A Large Scale Database for 3D Object Recognition (2016, background): “[9,24,42,33,15,39]), as the field has benefited from the introduction of several important databases that provide 3D annotations to 2D objects.”
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation (2019, background): “[38] retrieve shape components from a large dataset and deform the assembled shape to fit the observed image.”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
Cross-Domain Self-Supervised Multi-task Feature Learning Using Synthetic Imagery (2017, methodology): “Synthetic data for vision CAD models have been used for various vision tasks such as 2D-3D alignment [6, 4], object detection [53], joint pose estimation and image-shape alignment [64, 27].”
Single-view reconstruction via joint analysis of image and shape collections (2015, background): “The correspondences connect the image sets I and R , ultimately enabling inference about the three-dimensional structure of objects depicted in natural images.”
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (2015, background): “Another line of work tried to solve single-image reconstruction by finding the nearest neighbor in the shape collection followed by a refinement step [23], [24].”
Shape Completion from a Single RGBD Image (2017, methodology): “Global non-rigid alignment [29] often produces a good initial solution, which is computed from the deformed template model M i that aligns best with I .”