Automatic photo pop-up

By Derek Hoiem, Alexei A. Efros, Martial Hebert. 2005

760 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, 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 Graphics and Computer-Aided Design

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, background): “[15] categorise image regions into ground-plane, vertical plane or sky from a single image and use it to generate “pop-ups” by decomposing the image into planes [14].”
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…”
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network (2014, background): “In turn, such relations help provide richer representations of objects and their environment, often leading to improvements in existing recognition tasks [18], as well as enabling many further applications such as 3D modeling [16, 6], physics and support models [18], robotics [4, 14], and potentiall”
View Synthesis by Appearance Flow (2016, background): “Geometric approaches try to first estimate (or fake) the approximate underlying 3D structure of the object, and then apply some transformation to the pixels in the input image to produce the output [3,4,5,6,7,8,9].”
Geometric context from a single image (2005, background): “The details on how to construct these models and additional results are presented in our companion graphics paper [12].”
Unsupervised Learning of Depth and Ego-Motion from Video (2017, methodology): “Like our approach, these techniques only learn from image observations of the world, unlike methods that require explicit depth for training, e.g., [20, 42, 7, 27, 30].”
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, neutral): “based formulations [3], simple geometric assumptions [2],”
Dual Attention Guided Gaze Target Detection in the Wild (2021, background): “Early works [19, 21, 23] make an effort to exploit some statistically meaningful monocular cues (e.”
Single View Reconstruction of Curved Surfaces (2006, methodology): “[6] apply methods from the recent object recognition literature to learn texture and segmentation cues for a number of common object classes (e.”
What, where and who? Classifying events by scene and object recognition (2007, methodology): “We choose to demonstrate the usefulness of the layout/geometry information by using a simple estimation of 3 geometry cues: sky at infinity distance, vertical structure of the scene, and ground plane of the scene [8].”
Digging Into Self-Supervised Monocular Depth Estimation (2018, background): “Various approaches, such as combining local predictions [19, 55], non-parametric scene sampling [24], through to end-to-end supervised learning [9, 31, 10] have been explored.”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
Example Based 3D Reconstruction from Single 2D Images (2006, background): “One approach [ 14 , 15] reconstructs outdoor scenes assuming they can be labelled as “ground,” “sky,” and “vertical” billboards.”
Learning generative models of mid-level structure in natural images (2012, background): “, 2004), or for generating simple 3D reconstructions from single photographs (Hoiem et al., 2005).”
Recovering Surface Layout from an Image (2007, background): “In Hoiem et al. (2005), we show that our main surface labels and a horizon estimate are sufficient to reconstruct coarse, scaled 3D models of many outdoor scenes. By fitting the ground-vertical intersection in the image, we are able to “pop up” the vertical surfaces from the ground. Figure 22 shows ”