Real-time understanding in video is crucial in various AI applications such as autonomous driving. This work presents a fast single-shot segmentation strategy for video scene understanding. The proposed net, called S3-Net, quickly locates and segments target sub-scenes, meanwhile extracts structured time-series semantic features as inputs to an LSTM-based spatio-temporal model. Utilizing tensorization and quantization techniques, S3-Net is intended to be lightweight for edge computing. Experiments using CityScapes, UCF11, HMDB51 and MOMENTS datasets demonstrate that the proposed S3-Net achieves an accuracy improvement of 8.1% versus the 3D-CNN based approach on UCF11, a storage reduction of 6.9x and an inference speed of 22.8 FPS on CityScapes with a GTX1080Ti GPU.
StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception
Institut Pascal ISPR (Image, Systems of Perception, Robotics), Universite Clermont Auvergne INP / CNRS（帕斯卡尔研究所（图像、感知系统、机器人），克莱蒙特大学INP/CNRS）；Institute for Intelligent Systems at Esslingen University of Applied Sciences（埃斯林根应用科学大学智能系统研究所）
LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Prediction
State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室）；Beihang University（北京航空航天大学）；School of Computer Science and Information Engineering（计算机科学与信息工程学院）；Hefei University of Technology（合肥工业大学）；Hangzhou Innovation Institute（杭州创新研究院）
FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；School of Electrical and Information Engineering, Tianjin University（天津大学电气自动化与信息工程学院）
FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories
School of Intelligent Systems Engineering, Sun Yat-sen University（智能系统工程学院，中山大学）；Guangdong Provincial Key Laboratory of Intelligent Transportation Systems（广东省智能交通系统重点实验室）；Pengcheng Laboratory（鹏城实验室）
Modern surgeries are performed in complex and dynamic settings, including ever-changing interactions between medical staff, patients, and equipment. The holistic modeling of the operating room (OR) is, therefore, a challenging but essential task, with the potential to optimize the performance of surgical teams and aid in developing new surgical technologies to improve patient outcomes. The holistic representation of surgical scenes as semantic scene graphs (SGG), where entities are represented as nodes and relations between them as edges, is a promising direction for fine-grained semantic OR u…
L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学网络系统与控制研究所）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Zhejiang Guoli Security Technology Co., Ltd.（浙江国利安全科技有限公司）
Monocular depth estimation can play an important role in addressing the issue of deriving scene geometry from 2D images. It has been used in a variety of industries, including robots, self-driving cars, scene comprehension, 3D reconstructions, and others. The goal of our method is to create a lightweight machine-learning model in order to predict the depth value of each pixel given only a single RGB image as input with the Unet structure of the image segmentation network. We use the NYU Depth V2 dataset to test the structure and compare the result with other methods. The proposed method achiev…
DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activat…
Camera relocalization involving a prior 3D reconstruction plays a crucial role in many mixed reality and robotics applications. Estimating the camera pose directly with respect to pre-built 3D models can be prohibitively expensive for several applications with limited storage and/or communication bandwidth. Although recent scene and absolute pose regression methods have become popular for efficient camera localization, most of them are computation-resource intensive and difficult to obtain a real-time inference with high accuracy constraints. This study proposes a simple scene regression metho…
Efficient scene text image super-resolution with semantic guidance
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Videt Technology（Videt科技）；Innovation Center of Calligraphy and Painting Creation Technology, MCT（MCT书画创作技术创新中心）
Tsinghua University（清华大学）；University of Science and Technology, Beijing（北京科技大学）
Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have achieved acceptable performance. However, when facing complex scenes, since image contains a large amount of classes, it becomes difficult to learn visual appearance based on image tags. In this case, image-level annotations are not effective in providing information. Therefore, we set up a new task in which only one annotated pixel is provided for each category. B…
Sterilizable Scene Graph Generation for Operating Rooms
Technical University of Darmstadt（达姆施塔特工业大学）；ImFusion GmbH（ImFusion有限公司）；Carl Zeiss AG（卡尔蔡司股份公司）；University Medical Center Mainz（美因茨大学医学中心）；Inria Center at University Côte d’Azur（蔚蓝海岸大学法国国家信息与自动化研究所中心）
NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes
Department of Electronic and Electrical Engineering, Southern University of Science and Technology（电子与电气工程系，南方科技大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）
A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition
CVPR Unit, Indian Statistical Institute, Kolkata, India（印度统计研究所柯西拉分校CVPR单位）；Manipal University Jaipur, India（印度贾浦尔曼普尔大学）；University of Salford, UK（英国萨尔福德大学）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
Hunan University College of Computer Science（湖南大学计算机科学学院）；Hunan Normal University College of Information Science（湖南师范大学信息科学学院）；Hunan University（湖南大学）；Hunan Normal University（湖南师范大学）
NVIDIA Research（英伟达研究院）；Technical University of Munich（慕尼黑工业大学）
Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments (\eg gonioreflectometers, light stages, or multi-camera domes), or requires the joint optimization of shape, illumination, and reflectance, which is often computationally too expensive (\eg hours of running time) for real-time applications. Moreover, most prior work requires HDR images as input which further complicates the capture process. In this paper, we…
State Key Laboratory of Optical Instrumentation, Zhejiang University, China（浙江大学光学仪器国家重点实验室）；Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany（卡尔斯鲁厄理工学院人机与机器人研究所）
Aerial pixel-wise scene perception of the surrounding environment is an important task for UAVs (Unmanned Aerial Vehicles). Previous research works mainly adopt conventional pinhole cameras or fisheye cameras as the imaging device. However, these imaging systems cannot achieve large Field of View (FoV), small size, and lightweight at the same time. To this end, we design a UAV system with a Panoramic Annular Lens (PAL), which has the characteristics of small size, low weight, and a 360-degree annular FoV. A lightweight panoramic annular semantic segmentation neural network model is designed to…
Chungnam National University（忠南国立大学）；Pusan National University（釜山国立大学）
Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices. To this end, we suggest a distillation-based channel pruning method for the alpha matting networks. In the pruning step, we remove channels of a student network having fewer impacts on mimicking the knowledge of a teacher network. Then, the pruned lightweight student network is trained by the same distillation loss. A lightweigh…
We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow, along with 3D segmentation heads. On the SemanticKITTI benchmark, our method performs on par on semantic completion and better on occupancy completion than all other published methods -- while being significantly lighter and faster. As such it provides a great performance/speed trade-off for mobile-robotics applications. The ablation studies demonstrate our met…
Anhui Institute of Optics and Fine Mechanics, and Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院安徽光学精密机械研究所）；University of Science and Technology of China（中国科学技术大学）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
Mapping and localization are two essential tasks for mobile robots in real-world applications. However, largescale and dynamic scenes challenge the accuracy and robustness of most current mature solutions. This situation becomes even worse when computational resources are limited. In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness. Different from previous methods, our method does not need a prior constructed precise geometric map, which greatly releases the storage burden, especially for large-scale navigation. We use ob…
PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Delft University of Technology（代尔夫特理工大学）；Jiangsu University of Technology（江苏理工学院）；Hong Kong Metropolitan University（香港都会大学）
Ecole Centrale de Nantes（南特中央理工学院）；Hera-MI, SAS（Hera-MI股份有限公司）
We study the fully convolutional neural networks in the context of malignancy detection for breast cancer screening. We work on a supervised segmentation task looking for an acceptable compromise between the precision of the network and the computational complexity.
Indirect Time-of-Flight cameras (iToF) are low-cost devices that provide depth images at an interactive frame rate. However, they are affected by different error sources, with the spotlight taken by Multi-Path Interference (MPI), a key challenge for this technology. Common data-driven approaches tend to focus on a direct estimation of the output depth values, ignoring the underlying transient propagation of the light in the scene. In this work instead, we propose a very compact architecture, leveraging on the direct-global subdivision of transient information for the removal of MPI and for the…
InterDigital Research & Innovation（InterDigital 研发创新机构）
In this paper we address the problem of view synthesis from large baseline light fields, by turning a sparse set of input views into a Multi-plane Image (MPI). Because available datasets are scarce, we propose a lightweight network that does not require extensive training. Unlike latest approaches, our model does not learn to estimate RGB layers but only encodes the scene geometry within MPI alpha layers, which comes down to a segmentation task. A Learned Gradient Descent (LGD) framework is used to cascade the same convolutional network in a recurrent fashion in order to refine the volumetric …
Sabaragamuwa University of Sri Lanka（斯里兰卡萨伯勒格穆沃大学）
Automatic tomato disease recognition from leaf images is vital to avoid crop losses by applying control measures on time. Even though recent deep learning-based tomato disease recognition methods with classical training procedures showed promising recognition results, they demand large labelled data and involve expensive training. The traditional deep learning models proposed for tomato disease recognition also consume high memory and storage because of a high number of parameters. While lightweight networks overcome some of these issues to a certain extent, they continue to show low performan…
