3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints

By Fred Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. International Journal of Computer Vision, 2006

463 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6f3b1d94193a76f9f06d26e67cb22fd31aa735f

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

A multi-view probabilistic model for 3D object classes (2009, methodology): “Notably, [3, 32, 8, 24] have proposed methods for identifying and recognizing single objects such as a cereal box or a Teddy bear, under arbitrary viewing conditions.”
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (2018, methodology): “For objects of rich textures, traditional methods [24, 32, 1] detect local keypoints robustly, so the object pose is estimated both efficiently and accurately, even under cluttered scenes and severe occlusions.”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “This intermediate representation provides coarse information about the shape and its inference is a well studied problem in computer vision [29], [30], [31], [32], [33], [34], [35].”
Segmentation-Driven 6D Object Pose Estimation (2018, methodology): “Traditionally, it has been handled by establishing correspondences between the object’s known 3D model and 2D pixel locations, followed by using the Perspective-n-Point (PnP) algorithm to compute the 6 pose parameters [19, 38, 43].”
PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (2019, methodology): “Classical methods [30, 42, 2] are able to detect 2D keypoint of objects with rich texture efficiently.”
3D generic object categorization, localization and pose estimation (2007, background): “As such, however, the model of [20] fails to provide the necessary flexibility to handle the intra-class variability within each object category.”
3D ShapeNets: A deep representation for volumetric shapes (2014, unknown): “modelbased keypoint matching to nearest neighbors [24, 31]).”
Real-Time Seamless Single Shot 6D Object Pose Prediction (2017, methodology): “There are many fast keypoint and edge-based methods [21, 31, 36] that are effective for textured objects.”
Fast Single Shot Detection and Pose Estimation (2016, background): “Initially, research on the topic focused primarily on instance-level pose estimation [20, 1, 13, 3].”
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation (2017, unknown): “These include keypoint matching between 2D images and their corresponding 3D CAD models [1, 5, 37], or aligning 3D-reconstructed models with ground-truth models to recover the object poses [28, 9].”
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (2019, methodology): “Classical methods rely on detecting and matching keypoints with known object models [1, 7, 9, 27, 44].”
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views (2015, unknown): “, [10, 34, 45], typically based on SIFT matching [37] with geometric constraints.”
3D ShapeNets for 2.5D Object Recognition and Next-Best-View Prediction (2014, background): “Even though there are many theories about 3D representation [4, 18], the success of 3D-based methods is largely limited to instance recognition, using model-based keypoint matching [20, 24].”
3D-FUTURE: 3D Furniture Shape with TextURE (2020, unknown): “Rothganger et al., 2006).”
Fast 3D recognition and pose using the Viewpoint Feature Histogram (2010, background): “In [18], the authors propose a system for recognizing 3D objects in photographs.”