Related papers: DepthMatch: Semi-Supervised RGB-D Scene Parsing th…
Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue,…
We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic…
Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…
Semantic labeling of RGB-D scenes is crucial to many intelligent applications including perceptual robotics. It generates pixelwise and fine-grained label maps from simultaneously sensed photometric (RGB) and depth channels. This paper…
Vision-based perception and reasoning is essential for scene understanding in any autonomous system. RGB and depth images are commonly used to capture both the semantic and geometric features of the environment. Developing methods to…
For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously understand the higher level meaning…
Aligning partial views of a scene into a single whole is essential to understanding one's environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can…
In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for…
We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in RGB, depth, and normal information of a planar patch in an…
Captioning images is a challenging scene-understanding task that connects computer vision and natural language processing. While image captioning models have been successful in producing excellent descriptions, the field has primarily…
Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised…
Sparse depth measurements are widely available in many applications such as augmented reality, visual inertial odometry and robots equipped with low cost depth sensors. Although such sparse depth samples work well for certain applications…
Although well-known large-scale datasets, such as ImageNet, have driven image understanding forward, most of these datasets require extensive manual annotation and are thus not easily scalable. This limits the advancement of image…
Spatial visual perception is a fundamental requirement in physical-world applications like autonomous driving and robotic manipulation, driven by the need to interact with 3D environments. Capturing pixel-aligned metric depth using RGB-D…
RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC). SSC…
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases such as highly…
For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology in challenging lighting conditions. Thermal signal is an informative additional channel that can bring to light the…
Accurate dense depth estimation is crucial for autonomous vehicles to analyze their environment. This paper presents a non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image. To achieve this…
Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing. While deep learning methods have achieved good results in…
Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is to take full advantage of their complementary nature, aiming…