Related papers: Learning Hierarchical Shape Segmentation and Label…

Segmenting object parts such as cup handles and animal bodies is important in many real-world applications but requires more annotation effort. The largest dataset nowadays contains merely two hundred object categories, implying the…

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…

We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature…

Urban facade segmentation from automatically acquired imagery, in contrast to traditional image segmentation, poses several unique challenges. 360-degree photospheres captured from vehicles are an effective way to capture a large number of…

Labeling images for visual segmentation is a time-consuming task which can be costly, particularly in application domains where labels have to be provided by specialized expert annotators, such as civil engineering. In this paper, we…

Scene parsing, or semantic segmentation, consists in labeling each pixel in an image with the category of the object it belongs to. It is a challenging task that involves the simultaneous detection, segmentation and recognition of all the…

Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in…

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic…

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to…

In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a…

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect.…

Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for training are typically limited in quantity compared to the 2D images counterpart. In this work, we deal with the data scarcity challenge of 3D…

Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this paper, we demonstrate that carefully designed data engines can leverage web-curated, unlabeled videos…

This paper describes a novel method of training a semantic segmentation model for scene recognition of agricultural mobile robots exploiting publicly available datasets of outdoor scenes that are different from the target greenhouse…

Most approaches that tackle the problem of node classification consider nodes to be similar, if they have shared neighbors or are close to each other in the graph. Recent methods for attributed graphs additionally take attributes of…

Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic…

Distributed learning paradigms such as federated learning often involve transmission of model updates, or gradients, over a network, thereby avoiding transmission of private data. However, it is possible for sensitive information about the…

Open-vocabulary 3D segmentation enables exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances but struggle with…

Shape assembly composes complex shapes geometries by arranging simple part geometries and has wide applications in autonomous robotic assembly and CAD modeling. Existing works focus on geometry reasoning and neglect the actual physical…

This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree. This model extends the traditional…