Related papers: Efficient RGB-D Scene Understanding via Multi-task…
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which…
We present a system for 3D semantic scene perception consisting of a network of distributed smart edge sensors. The sensor nodes are based on an embedded CNN inference accelerator and RGB-D and thermal cameras. Efficient vision CNN models…
This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…
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…
We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans. The core idea of our method is to jointly learn from both geometric and color signal, thus enabling accurate instance…
In this work we address the problem of indoor scene understanding from RGB-D images. Specifically, we propose to find instances of common furniture classes, their spatial extent, and their pose with respect to generalized class models. To…
Multimodal deep sensor fusion has the potential to enable autonomous vehicles to visually understand their surrounding environments in all weather conditions. However, existing deep sensor fusion methods usually employ convoluted…
This paper provides a review of deep learning applications in scene understanding in autonomous robots, including innovations in object detection, semantic and instance segmentation, depth estimation, 3D reconstruction, and visual SLAM. It…
We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simultaneously denoise the 3D poses and geometries of all objects…
Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous…
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…
Surgical scene understanding is a key technical component for enabling intelligent and context aware systems that can transform various aspects of surgical interventions. In this work, we focus on the semantic segmentation task, propose a…
Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications such as robot grasping and autonomous driving. In this paper, we address this…
Scene understanding plays an important role in several high-level computer vision applications, such as autonomous vehicles, intelligent video surveillance, or robotics. However, too few solutions have been proposed for indoor/outdoor scene…
Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce…
Reasoning about complex visual scenes involves perception of entities and their relations. Scene graphs provide a natural representation for reasoning tasks, by assigning labels to both entities (nodes) and relations (edges). Unfortunately,…
Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but…
One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of walls, which must…
Imitation Learning can train robots to perform complex and diverse manipulation tasks, but learned policies are brittle with observations outside of the training distribution. 3D scene representations that incorporate observations from…
To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…