FPM: Fine Pose Parts-Based Model with 3D CAD Models

Lim, Joseph J.; Khosla, Aditya; Torralba, Antonio

doi:10.1007/978-3-319-10599-4_31

Cited by 71 publications

(59 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A natural approach to estimating the pose of an image I ∈ I is to retrieve the most similar rendered images and use their known camera poses to estimate the pose of I [Aubry et al 2014;Lim et al 2014;Su et al 2014]. We found that the results produced by this approach are noisy, as illustrated in Figure 3.…”

Section: Camera Pose Estimationmentioning

confidence: 99%

Single-view reconstruction via joint analysis of image and shape collections

2015

View full text Add to dashboard Cite

Web image searchReconstructed 3D modelsFigure 1: Our approach reconstructs objects depicted in images, even if each object is only shown in a single image. Left: Web image search for "windsor chair", first page results. Right: 3D models automatically generated by our approach for these images. AbstractWe present an approach to automatic 3D reconstruction of objects depicted in Web images. The approach reconstructs objects from single views. The key idea is to jointly analyze a collection of images of different objects along with a smaller collection of existing 3D models. The images are analyzed and reconstructed together. Joint analysis regularizes the formulated optimization problems, stabilizes correspondence estimation, and leads to reasonable reproduction of object appearance without traditional multi-view cues.

show abstract

Section: Camera Pose Estimationmentioning

confidence: 99%

Single-view reconstruction via joint analysis of image and shape collections

2015

View full text Add to dashboard Cite

show abstract

“…Since our approach is based on object parts, it is also related to works such as [26,27,45,20] that mostly focus on category rather than instance detection. These works were mostly motivated by the success of the Deformable Part Model [7] developed for 2D detection, which was extended successfully to 3D, e.g.…”

Section: Related Workmentioning

confidence: 99%

“…Relying on parts for 3D object detection is not new [12,27,33,20,45]. The 1 All the figures of this work are best seen in colors.…”

Section: Introductionmentioning

confidence: 98%

“…3D object detection and tracking methods have undergone impressive improvements in recent years [5,27,13,4,30,25,39,17,1,45,38,20,35,44]. However, each of the current approaches has its own weaknesses: Many of these approaches [5,13,1,35] rely on a depth sensor, which would fail on metallic objects or outdoor scenes; methods based on feature points [25,17] expect textured objects; those based on edges [4,39] are sensitive to cluttered background; most of these methods [13,27,30,38,11,45,20] are not robust to occlusion.…”

Section: Introductionmentioning

confidence: 99%

“…However, each of the current approaches has its own weaknesses: Many of these approaches [5,13,1,35] rely on a depth sensor, which would fail on metallic objects or outdoor scenes; methods based on feature points [25,17] expect textured objects; those based on edges [4,39] are sensitive to cluttered background; most of these methods [13,27,30,38,11,45,20] are not robust to occlusion. We also want a method fast enough for interactive 3D applications.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

Crivellaro

Rad

Verdie

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We present a method that estimates in real-time and under challenging conditions the 3D pose of a known object. Our method relies only on grayscale images since depth cameras fail on metallic objects; it can handle poorly textured objects, and cluttered, changing environments; the pose it predicts degrades gracefully in presence of large occlusions. As a result, by contrast with the state-of-the-art, our method is suitable for practical Augmented Reality applications even in industrial environments. To be robust to occlusions, we first learn to detect some parts of the target object. Our key idea is to then predict the 3D pose of each part in the form of the 2D projections of a few control points. The advantages of this representation is three-fold: We can predict the 3D pose of the object even when only one part is visible; when several parts are visible, we can combine them easily to compute a better pose of the object; the 3D pose we obtain is usually very accurate, even when only few parts are visible.

show abstract

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

Huang

Zhu

et al. 2018

Lecture Notes in Computer Science

120

107

View full text Add to dashboard Cite

We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes. The proposed HSG captures three essential and often latent dimensions of the indoor scenes: i) latent human context, describing the affordance and the functionality of a room arrangement, ii) geometric constraints over the scene configurations, and iii) physical constraints that guarantee physically plausible parsing and reconstruction. We solve this joint parsing and reconstruction problem in an analysis-by-synthesis fashion, seeking to minimize the differences between the input image and the rendered images generated by our 3D representation, over the space of depth, surface normal, and object segmentation map. The optimal configuration, represented by a parse graph, is inferred using Markov chain Monte Carlo (MCMC), which efficiently traverses through the non-differentiable solution space, jointly optimizing object localization, 3D layout, and hidden human context. Experimental results demonstrate that the proposed algorithm improves the generalization ability and significantly outperforms prior methods on 3D layout estimation, 3D object detection, and holistic scene understanding.

show abstract

FPM: Fine Pose Parts-Based Model with 3D CAD Models

Cited by 71 publications

References 32 publications

Single-view reconstruction via joint analysis of image and shape collections

Single-view reconstruction via joint analysis of image and shape collections

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

Contact Info

Product

Resources

About