• Corpus ID: 12556675

Semantic-Aware Depth Super-Resolution in Outdoor Scenes

  title={Semantic-Aware Depth Super-Resolution in Outdoor Scenes},
  author={Miaomiao Liu and Mathieu Salzmann and Xuming He},
While depth sensors are becoming increasingly popular, their spatial resolution often remains limited. Depth super-resolution therefore emerged as a solution to this problem. Despite much progress, state-of-the-art techniques suffer from two drawbacks: (i) they rely on the assumption that intensity edges coincide with depth discontinuities, which, unfortunately, is only true in controlled environments; and (ii) they typically exploit the availability of high-resolution training depth maps… 
Real-time Semantic Segmentation-based Depth Upsampling using Deep Learning
A new real-time depth upsampling method based on convolutional neural networks (CNNs) that uses the local context provided by semantic information and uses dilated convolutions as means to cope with sparse inputs from cost-effective depth sensors.


Single image depth estimation from predicted semantic labels
This work first performs a semantic segmentation of the scene and uses the semantic labels to guide the 3D reconstruction and incorporates semantic features to achieve state-of-the-art results with a significantly simpler model than previous works.
Learning Depth from Single Monocular Images
This work begins by collecting a training set of monocular images (of unstructured outdoor environments which include forests, trees, buildings, etc.) and their corresponding ground-truth depthmaps, and applies supervised learning to predict the depthmap as a function of the image.
Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras
  • Ju Shen, S. Cheung
  • Mathematics, Computer Science
    2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
A novel probabilistic model is proposed to capture various types of uncertainties in the depth measurement process among structured-light systems, using the use of depth layers to account for the differences between foreground objects and background scene, the missing depth value phenomenon, and the correlation between color and depth channels.
A Joint Intensity and Depth Co-sparse Analysis Model for Depth Map Super-resolution
A bimodal co-sparse analysis model is introduced, which is able to capture the interdependency of registered intensity and depth information and is exploited as a prior for solving inverse problems, which leads to an efficient algorithm for depth map super-resolution.
Depth Super Resolution by Rigid Body Self-Similarity in 3D
This work is to its knowledge the first to present a tailored analogue for depth images, and shows that its results are highly competitive with those of alternative techniques leveraging even a color image at the target resolution or a database of high-resolution depth exemplars.
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
This work proposes algorithms for object boundary detection and hierarchical segmentation that generalize the gPb-ucm approach of [2] by making effective use of depth information and shows how this contextual information in turn improves object recognition.
RGB-(D) scene labeling: Features and algorithms
The main objective is to empirically understand the promises and challenges of scene labeling with RGB-D and adapt the framework of kernel descriptors that converts local similarities (kernels) to patch descriptors to capture appearance (RGB) and shape (D) similarities.
Patch Based Synthesis for Single Depth Image Super-Resolution
This work presents an algorithm to synthetically increase the resolution of a solitary depth image using only a generic database of local patches, and shows how important further depth-specific processing, such as noise removal and correct patch normalization, dramatically improves results.
Semantic Labeling of 3D Point Clouds for Indoor Scenes
This paper proposes a graphical model that captures various features and contextual relations, including the local visual appearance and shape cues, object co-occurence relationships and geometric relationships, and applies these algorithms successfully on a mobile robot for the task of finding objects in large cluttered rooms.
Depth Enhancement via Low-Rank Matrix Completion
  • Si Lu, Xiaofeng Ren, Feng Liu
  • Mathematics, Computer Science
    2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
A depth map enhancement algorithm that performs depth map completion and de-noising simultaneously, based on the observation that similar RGB-D patches lie in a very low-dimensional subspace and as a low-rank matrix completion problem.