A multi-view probabilistic model for 3D object classes

By Min Sun, Hao Su, Silvio Savarese, Li Fei-Fei. 2009

138 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning 3D Object Categories by Looking Around Them (2017, methodology): “Only a few works have used videos [37, 35].”
Relating Things and Stuff via ObjectProperty Interactions (2014, unknown): “[8], [9] work best.”
Reconstructing PASCAL VOC (2014, background): “[16, 24]) and that it will facilitate progress in this direction since it provides the first semi-automatic solution to 3D model acquisition of detection data, which has possibly been the main obstacle to any previous attempts to 3D model-based recognition.”
Modeling Occlusion by Discriminative AND-OR Structures (2013, unknown): “DPM [21] [12] [28] ours”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Relating Things and Stuff via Object Property Interactions (methodology): “In the first category, we find that methods based on pictorial structures (i.e., Felzenszwalb et al. [1]), pyramid structures (i.e., Grauman and Darrell [2]), generalized Hough transform [3]–[7], or multi-view model [8], [9] work best.”
Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images (2014, background): “More recently, Stark et al. (2010); Liebelt & Schmid (2010); Sun et al. (2009) used 3D CAD models as their only source of labeled data, but limited their work to a few categories like cars and motorcycles.”
3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model (2012, background): “Several authors augmented the multi-view representation with weak 3D information by linking the features or parts across views [17, 18, 19, 20, 21].”
Learning Deep Object Detectors from 3D Models (2014, methodology): “More recently, [21, 10, 23] used 3D CAD models as their only source of labeled data, but limited their work to a few categories like cars and motorcycles.”
Discriminative Mixture-of-Templates for Viewpoint Classification (2010, background): “We also show a significantly higher (4-view) viewpoint classification rate on the VOC2006 car database compared to the earlier work of [6] and [7].”
From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains (2014, background): “Most previous work utilizing 3D models focuses on predicting the 3D pose or viewpoint of an object in 2D test images [14, 18, 22, 23, 25], or categorizing an object from an arbitrary novel viewpoint [21].”
Analyzing 3D Objects in Cluttered Images (2012, background): “3D models: One can also directly reason about local features and their geometric arrangement in a 3D coordinate system [23] [25] [34].”
FPM: Fine Pose Parts-Based Model with 3D CAD Models (2014, background): “Recently, there has been an increasing interest in utilizing 3D models for object detection and pose estimation [39,27,10,19,34].”
Diagnosing Error in Object Detectors (2012, unknown): “, [10–12]).”
Holistic Scene Understanding for 3D Object Detection with RGBD Cameras (2013, background): “[25] Min Sun, Hao Su, Silvio Savarese, and Li Fei-Fei.”