Image harmonization has been significantly advanced with large-scale harmonization dataset. However, the current way to build dataset is still labor-intensive, which adversely affects the extendability of dataset. To address this problem, we propose to construct rendered harmonization dataset with fewer human efforts to augment the existing real-world dataset. To leverage both real-world images and rendered images, we propose a cross-domain harmonization network to bridge the domain gap between two domains. Moreover, we also employ well-designed style classifiers and losses to facilitate cross-domain knowledge transfer. Extensive experiments demonstrate the potential of using rendered images for image harmonization and the effectiveness of our proposed network.
SDU Robotics（南丹麦大学机器人研究所）；University of Southern Denmark（南丹麦大学）
Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance. While the use of synthetic training data prevents the need for manual annotation, there is currently a large performance gap between methods trained on real and synthetic data. This paper introduces a new method, which bridges this gap. Most methods trained on synthetic data use 2D images, as domain randomization in 2D is more developed. To obtain precise po…
Integrating a foreground object into a background scene with illumination harmonization is an important but challenging task in computer vision and augmented reality community. Existing methods mainly focus on foreground and background appearance consistency or the foreground object shadow generation, which rarely consider global appearance and illumination harmonization. In this paper, we formulate seamless illumination harmonization as an illumination exchange and aggregation problem. Specifically, we firstly apply a physically-based rendering method to construct a large-scale, high-quality …
We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding bo…
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the simulator$-$such as lighting, pose, object textures, etc.$-$are randomized in non-realistic ways to force the neural network to learn the essential features of the object of interest. We explore the importance of these parameters, showing that it is possible to produce a network with compelling performance using only non-artistically-generated synthetic data. …
6D pose recognition has been a crucial factor in the success of robotic grasping, and recent deep learning based approaches have achieved remarkable results on benchmarks. However, their generalization capabilities in real-world applications remain unclear. To overcome this gap, we introduce 6IMPOSE, a novel framework for sim-to-real data generation and 6D pose estimation. 6IMPOSE consists of four modules: First, a data generation pipeline that employs the 3D software suite Blender to create synthetic RGBD image datasets with 6D pose annotations. Second, an annotated RGBD dataset of five house…
PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
Fudan University（复旦大学）；University of Michigan（密歇根大学）；Shanghai Key Lab of Intelligent Information Processing（上海市智能信息处理重点实验室）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）
Bridging the Ex-Vivo to In-Vivo Gap: Synthetic Priors for Monocular Depth Estimation in Specular Surgical Environments
RoCAL, Rochester Institute of Technology（罗切斯特理工学院RoCAL实验室）；Department of Otolaryngology Head and Neck Surgery, University of Rochester Medical Center（罗切斯特大学医学中心耳鼻喉科与头颈外科部门）；University of Washington, Department of Otolaryngology–Head and Neck Surgery（华盛顿大学耳鼻喉科与头颈外科部门）
The University of Sydney（悉尼大学）；Birkbeck College, University of London（伦敦大学伯贝克学院）
Extracting accurate foregrounds from natural images benefits many downstream applications such as film production and augmented reality. However, the furry characteristics and various appearance of the foregrounds, e.g., animal and portrait, challenge existing matting methods, which usually require extra user inputs such as trimap or scribbles. To resolve these problems, we study the distinct roles of semantics and details for image matting and decompose the task into two parallel sub-tasks: high-level semantic segmentation and low-level details matting. Specifically, we propose a novel Glance…
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Recently, learning-based approaches for 3D model reconstruction have attracted attention owing to its modern applications such as Extended Reality(XR), robotics and self-driving cars. Several approaches presented good performance on reconstructing 3D shapes by learning solely from images, i.e., without using 3D models in training. Challenges, however, remain in texture generation due to the gap between 2D and 3D modals. In previous work, the grid sampling mechanism from Spatial Transformer Networks was adopted to sample color from an input image to formulate texture. Despite its success, the e…
Google Brain（谷歌大脑）；University of California Berkeley（加州大学伯克利分校）；X, The Moonshot Factory（X，登月工厂）
Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need for manually engineering or prior learning a perception system. However, data for RL is collected via running an agent in the desired environment, and for applications like robotics, running a robot in the real world may be extremely costly and time consuming. Simulated training offers an appealing alternative, but ensuring that policies trained in simulation can transfer effectively into the real world requires additional mach…
Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challenges
OceanScan Marine Systems & Technology（OceanScan海洋系统与技术公司）；INESC INOV-Lab（INESC INOV实验室）；ISRC (ISEP/P.PORTO)（ISRC（波尔图高等工程学院/波尔图大学））；Faculty of Engineering, University of Porto (FEUP)（波尔图大学工程学院（FEUP））
