Multi-view object class detection with a 3D geometric model

By Joerg Liebelt, Cordelia Schmid. 2010

233 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

Unsupervised Domain Adaptation by Backpropagation (2014, background): “One particularly important example is synthetic or semi-synthetic imagery, which may come in abundance and fully labeled, but which inevitably look different from real data [13, 20, 23, 21].”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “In addition, the 2D DPM model can be extended to 3D [5, 12] to facilitate multiActions”
ShapeNet: An Information-Rich 3D Model Repository (2015, background): “Large datasets such as this and others (e.g., [14, 18]) have revitalized data-driven algorithms for recognition, detection, and editing of images, which have revolutionized computer vision.”
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views (2015, methodology): “3D Object Detection Most 3D object detection methods are based on representing objects with discriminative features for points [4], patches [6] and parts [19, 29, 34], or by exploring topological structures [15, 2, 3].”
Semantically-enriched 3D models for common-sense knowledge (2015, neutral): “For instance, prior work in vision has used 3D models for detection [16, 22] and fine-grained classification [15].”
Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories (2016, methodology): “Images rendered from 3D models are widely used in deep learning, e.g. [31, 19, 13, 23] for training object detectors and viewpoint classiﬁers.”
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints (2016, background): “ signiﬁcance of object pose estimation from a single-view image is also discussed in recent publications that synthesize 3D CAD models of objects into real images for learning real object recognition [16,17,13,18,19,20]. Papon and Schoeler [16] learned a CNN that takes the normal, intensity, and dep”
Back to the Future: Learning Shape Models from 3D CAD Data (2010, methodology): “[26] (cyan curve), Gill and Levine [11] (blue curve), and the very recent Liebelt and Schmid [14] (magenta curve).”
3D Object Representations for Fine-Grained Categorization (2013, unknown): “Similar to prior works in multi-view detection , we leverage 3D CAD models to generate synthetic training data [18] [37] [32] [24] .”
Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes (2011, background): “As such, they work even when the object is not textured enough to use feature point techniques and can directly provide a coarse estimation of the object pose.”
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.”
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].”
Play and Learn: Using Video Games to Train Computer Vision Models (2016, background): “[23], and Liebelt and Schmid [21] learn intermediate geometric descriptors from 3d models to per-SHAFAEI form object detection.”
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.”
Sliding Shapes for 3D Object Detection in Depth Images (2014, background): “There are also works on using CAD models for training [31–36], but they are not for depth images.”
Teaching 3D geometry to deformable part models (2012, methodology): “While several approaches have successfully demonstrated the integration of 3D training data in the form of 3D CAD models [20] [28] and point clouds from structurefrom-motion [35] [1] [13] or depth sensors [30], their outputs are typically still limited to 2D BBs and associated viewpoint estimates,…”
Understanding Bayesian Rooms Using Composite 3D Object Models (2013, methodology): “The performance of our approach often exceeds that of state-of-the-art methods on the two tasks of room layout estimation and object recognition, as evaluated on two bench mark data sets used in this domain.”
Single image 3D object detection and pose estimation for grasping (2014, background): “Liebelt et al. work with a view space of rendered models in [10] and a generative geometry representation is developed in [11].”
Leveraging the Wisdom of the Crowd for Fine-Grained Recognition (2016, methodology): “[32], [38], we leverage 3D CAD models as a cheap and”