Tags2Parts: Discovering Semantic Regions from Shape Tags

Muralikrishnan, S.; Kim, Vladimir G.; Chaudhuri, Siddhartha

doi:10.1109/cvpr.2018.00309

Cited by 24 publications

(25 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weakly or semi-supervised strategies represent a compromise between supervised and unsupervised methods [54], [55]. A recent study [56] proposed a novel method for segmenting 3D objects, which strongly correlate with user-prescribed tags.…”

Section: Machine Learning-based Methodsmentioning

confidence: 99%

From 2D to 3D: Component Description for Partial Matching of Point Clouds

Zhang

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

We present a method to compute the descriptor of components of point clouds, therefore, a novel component-oriented partial matching of point clouds is achieved based on the component descriptor. We observe that 3D components can be constructed by stacking 2D shapes using certain criteria so that the centers of the 2D shapes form a curve called a skeletal curve that is the trajectory of the 2D shapes. In addition, the scaling factors of the 2D shapes also impact the shape of the 3D components. Motivated by these observations, the computation of the component descriptor that is termed 2to3SSC (from 2D to 3D: 2D Shape and Skeletal Curve) is formulated as a 2D shape and skeletal curve extraction problem, and the component-oriented partial matching of the point clouds is based on the dissimilarity measure of 2to3SSCs of the components. Furthermore, for the 2D shape matching, which is crucial to the matching of the components, we present a novel 2D shape descriptor called VDTL (Vertical Distances to the Tangent Line). The proposed method outperforms previously proposed methods because it simultaneously encodes the local and global features of the components as opposed to only encoding the local or partial features as in previous studies. Finally, the effectiveness and performance of 2to3SSCs are compared with those of stateof-the-art feature description and matching methods for different point cloud datasets. Further, the benefits and the applicability of the proposed method are demonstrated; favorable results are obtained for real-world point clouds of Terracotta fragments.INDEX TERMS Computer graphics, point clouds, partial matching, 2D shape matching.

show abstract

Section: Machine Learning-based Methodsmentioning

confidence: 99%

From 2D to 3D: Component Description for Partial Matching of Point Clouds

Zhang

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Most methods on learning semantic shape segmentation are supervised, e.g., [9,20,21,29]. As a representative weakly supervised approach, Tags2Parts [14] obtains semantic part annotations from weak shape-level tags through a deep neural network, which is trained to classify the shape as having or lacking a part. AdaCoSeg [30] learns adaptive co-segmentation over a set of shapes using a group consistency loss.…”

Section: Related Workmentioning

confidence: 99%

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures

Niu¹,

Li²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field decoder, the part decoder is designed to decompose a sub-shape, via a two-way branched reconstruction, where each branch predicts a set of parameters defining a Gaussian to serve as a local point distribution for shape reconstruction. With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. Through extensive experiments and comparisons to state-of-the-art alternatives, we demonstrate the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.

show abstract

“…We compare BAE-NET with the state-of-the-art weakly supervised part labeling network, Tags2Parts [36]. Given a shape dataset and a binary label for each shape indicating whether a target part appears in it or not, Tags2Parts can separate out the target parts, with the binary labels as weak supervision.…”

Section: Comparison With Tags2partsmentioning

confidence: 99%

“…To compare results, we used the same metric as in [36]: Area Under the Curve (AUC) of precision/recall curves. For Shape (#parts) airplane (3) bag (2) cap (2) chair (3) chair* (4) mug (2) skateboard (2) [36] in every category, even though our network did not use the provided per-shape labels explicitly. each test point, we get its probability of being in each part by normalizing the branch outputs with a unit sum.…”

Section: Comparison With Tags2partsmentioning

confidence: 99%

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

Chen

Yin

Fisher

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

127

112

View full text Add to dashboard Cite

We treat shape co-segmentation as a representation learning problem and introduce BAE-NET, a branched autoencoder network, for the task. The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels. Specifically, the network takes an input shape and encodes it using a convolutional neural network, whereas the decoder concatenates the resulting feature code with a point coordinate and outputs a value indicating whether the point is inside/outside the shape. Importantly, the decoder is branched: each branch learns a compact representation for one commonly recurring part of the shape collection, e.g., airplane wings. By complementing the shape reconstruction loss with a label loss, BAE-NET is easily tuned for one-shot learning. We show unsupervised, weakly supervised, and one-shot learning results by BAE-NET, demonstrating that using only a couple of exemplars, our network can generally outperform state-of-the-art supervised methods trained on hundreds of segmented shapes. Code is available at https://github.com/czq142857/BAE-NET.

show abstract

Tags2Parts: Discovering Semantic Regions from Shape Tags

Cited by 24 publications

References 29 publications

From 2D to 3D: Component Description for Partial Matching of Point Clouds

From 2D to 3D: Component Description for Partial Matching of Point Clouds

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

Contact Info

Product

Resources

About