Dense Reconstruction Using 3D Object Shape Priors

By Amaury Dame, Victor Adrian Prisacariu, Carl Yuheng Ren, Ian David Reid. 2013

164 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

In 3D Vision & Pose

Citations in the corpus

Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, background): “There have also been attempts on using prior knowledge about the shape of 3D objects [6] in the absence of large amounts of data.”
Learning a Multi-View Stereo Machine (2017, methodology): “Learning has been used for multi-view reconstruction in the form of shape priors for objects [2, 9, 58, 20, 27, 52], or semantic class speciﬁc surface priors for scenes [22, 17, 45].”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, background): “For such cases object shape priors have been proposed [8], [14], [36].”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, methodology): “Thus, shape prior-based methods can work with fewer images and with fewer assumptions on the object reﬂectance function as shown in [17,18].”
Lifting Object Detection Datasets into 3D (2015, positive): “To account for differences between the 3D exemplars and the object depicted, Su and Guibas [26] choose a few exemplars that appear to be similar to the depicted shape and combine them to produce a single depth map.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “jects [57], [217] or prior knowledge about the expected structure in the scene, like smoothness as in DTAM [184], Manhattan constraints as in [80], or even the expected relationships between objects [10].”
CubeSLAM: Monocular 3-D Object SLAM (2018, background): “first build a SLAM point cloud map and then further detect and optimize 3-D object poses based on point cloud clustering and semantic information [16]–[18].”
Improved Adversarial Systems for 3D Object Generation and Reconstruction (2017, methodology): “Recent examples include: GP-LVMs [7], Convolutional Neural Networks [9], Recurrent Neural Networks [5], Deep Belief Networks [28], Generative Adversarial Networks [8, 26] and Deep Convolutional Auto-encoders [10].”
Mesh R-CNN (2019, background): “There is a broad line of work on multi-view reconstruction of objects and scenes, from classical binocular stereo [17, 53] to using shape priors [1, 2, 6, 21] and modern learning techniques [24, 26, 54].”
Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels (2017, methodology): “In contrast, existing methods first reconstruct a 3D model from the images and then fuse shape models into this 3D reconstruction [3, 11, 39].”
Patches, Planes and Probabilities: A Non-Local Prior for Volumetric 3D Reconstruction (2016, background): “, by constraining the set of plausible geometries [2, 11, 19] or by modeling class specific normal distributions [20,21].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “While previous approaches (Dame et al. (2013); Bao et al. (2013)) try to fit a parametric shape model to input data, Haene et al. (2014) model the local distribution of normals for an object.”
Implicit Surface Representations As Layers in Neural Networks (2019, background): “There have also been attempts on using prior knowledge about the shape of 3D objects [6] in the absence of large amounts of data.”
Joint 3d Estimation of Vehicles and Scene Flow (2015, methodology): “Recently, (Prisacariu et al., 2013) proposed an efﬁcient way to compress prior information from CAD models with complex shape variations using Gaussian Process Latent Variable Models.”
Displets: Resolving stereo ambiguities using object knowledge (2015, background): “In contrast to [1,7], the number of objects is unknown in our case.”
A Field Model for Repairing 3D Shapes (2016, methodology): “For example, in [6], image-based object detection method [8] was used to detect the 2D image of an object model, the 3D model was then computed and the pose was estimated.”
DUSt3R: Geometric 3D Vision Made Easy (2023, unknown): “Unconstrained image-based dense 3D reconstruction from multiple views is one of a few long-researched end-goals of computer vision [24, 72, 90].”
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision (2018, background): “tion as optimization problem over the corresponding (lowerdimensional) latent space [3, 10, 13, 22].”
Class Specific 3D Object Shape Priors Using Surface Normals (2014, background): “Object shape priors have recently attained much attention in the field of dense 3D reconstruction [3, 5].”