Related papers: Semantic Pose using Deep Networks Trained on Synth…
The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…
Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a…
Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…
Recognizing objects and scenes are two challenging but essential tasks in image understanding. In particular, the use of RGB-D sensors in handling these tasks has emerged as an important area of focus for better visual understanding.…
We propose a method at the intersection of Computer Vision and Computer Graphics fields, which automatically generates RGBD images using neural networks, based on previously seen and synchronized video, depth and pose signals. Since the…
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more…
This paper presents an approach for semantic place categorization using data obtained from RGB cameras. Previous studies on visual place recognition and classification have shown that, by considering features derived from pre-trained…
This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale…
This paper introduces key machine learning operations that allow the realization of robust, joint 6D pose estimation of multiple instances of objects either densely packed or in unstructured piles from RGB-D data. The first objective is to…
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…
The emergence of RGB-D sensors offered new possibilities for addressing complex artificial vision problems efficiently. Human posture recognition is among these computer vision problems, with a wide range of applications such as ambient…
Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…
While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-level object pose…
Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D…
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…
We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be…
The ability to endow maps of indoor scenes with semantic information is an integral part of robotic agents which perform different tasks such as target driven navigation, object search or object rearrangement. The state-of-the-art methods…
Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object…
We present an approach for recognizing all objects in a scene and estimating their full pose from an accurate 3D instance-aware semantic reconstruction using an RGB-D camera. Our framework couples convolutional neural networks (CNNs) and a…
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…