Sparse Depth-Guided Attention for Accurate Depth Completion: A Stereo-Assisted Monitored Distillation Approach
Huawei Cloud Computing Technology Co., Ltd.（华为云计算技术有限公司）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人学会）；Institute of Robotics and Intelligent Manufacturing, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）机器人与智能制造研究院）
Jia-Wei Guo, Hung-Chyun Chou, Sen-Hua Zhu, Chang-Zheng Zhang, Ming Ouyang, Ning Ding
This paper proposes a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we introduce a stereo-based model as a teacher model to improve the accuracy of the student model for depth completion. By minimizing the reconstruction error of a target image during ensemble distillation, we can avoid learning inherent error modes of completion-based teachers. We introduce an Attention-based Sparse-to-Dense (AS2D) module at the front layer of the student model to enhance its ability to extract global features from sparse depth. To provide self-supervised information, we also employ multi-view depth consistency and multi-scale minimum reprojection. These techniques utilize existing structural constraints to yield supervised signals for student model training, without requiring costly ground truth depth information. Our extensive experimental evaluation demonstrates that our proposed method significantly improves the accuracy of the baseline monitored distillation method.
University of Bologna（博洛尼亚大学）；China Agricultural University（中国农业大学）
In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches. This fact occurs for depth estimation based on either monocular or stereo, with the latter often providing a valid source of self-supervision for the former. In contrast, to soften typical stereo artefacts, we propose a novel self-supervised paradigm reversing the link between the two. Purposely, in order to train deep stereo networks, we distill knowledge through a monocular completion network. This architecture exploits single-image clues and few sparse points, sourced by t…
We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge distillation approach that yields a positive congruent training process, wherein a student model avoids learning the error modes of the teachers. In the absence of ground truth for model selection and training, our method, termed Monitored Distillation, allows a student to exploit a blind ensemble of teachers by selectively learning from predictions that best…
Huazhong University of Science and Technology（华中科技大学）；Baidu Inc.（百度公司）
In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation. The key designs of StereoDistill are: the X-component Guided Distillation~(XGD) for regression and the Cross-anchor Logit Distillation~(CLD) for classification. In XGD, instead of empirically adopting a threshold to select the high-quality teacher predictions as soft targets, we decompose the predicte…
A Lightweight Target-Driven Network of Stereo Matching for Inland Waterways
College of Artificial Intelligence, Tianjin University of Science and Technology（天津科技大学人工智能学院）；School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；Tianjin Institute of Navigation Instruments（天津航海仪器研究所）
Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the monocular depth estimation network by distilling disparity maps as proxy ground-truths. However, these studies naively distill the stereo knowledge without considering the comparative advantages of stereo-based and monocular depth estimation methods. In this paper, we propose to selectively distill the disparity maps for more reliable proxy supervision. Spec…
Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices
UBTech Robotics Corp（优必选机器人公司）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）；Beijing University of Posts and Telecommunications（北京邮电大学）
Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm, and can obtain the appropriate number of hidden layers in DBN. In this paper, our model is applied to a facial expression image data set, AffectNet. The system has higher classification capability than the traditional CNN. However, our model wa…
RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions
Department of Computer Science, City University of Hong Kong（城市大学计算机科学系）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所（CASIA））
Rutgers University（罗格斯大学）；University of Delaware（特拉华大学）
Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist in both modalities. However, accessing the data from superior modalities may not always be feasible. For example, in the case of 3D hand pose estimation, depth maps, point clouds, or stereo images usually capture better hand structures than RGB images, but most of them are expensive to be collected. In this paper, we propose a novel scheme to train the Stud…
In this paper, we introduce a deep multi-view stereo (MVS) system that jointly predicts depths, surface normals and per-view confidence maps. The key to our approach is a novel solver that iteratively solves for per-view depth map and normal map by optimizing an energy potential based on the locally planar assumption. Specifically, the algorithm updates depth map by propagating from neighboring pixels with slanted planes, and updates normal map with local probabilistic plane fitting. Both two steps are monitored by a customized confidence map. This solver is not only effective as a post-proces…
3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems. It is challenging to estimate the complete geometry and semantics of a scene solely from visual images, and accurate depth information is crucial for restoring 3D geometry. In this paper, we propose the first stereo SSC method named OccDepth, which fully exploits implicit depth information from stereo images (or RGBD images) to help the recovery of 3D geometric structures. The Stereo Soft Feature Assignment (Stereo-SFA) …
Feature representation learning is the key recipe for learning-based Multi-View Stereo (MVS). As the common feature extractor of learning-based MVS, vanilla Feature Pyramid Networks (FPNs) suffer from discouraged feature representations for reflection and texture-less areas, which limits the generalization of MVS. Even FPNs worked with pre-trained Convolutional Neural Networks (CNNs) fail to tackle these issues. On the other hand, Vision Transformers (ViTs) have achieved prominent success in many 2D vision tasks. Thus we ask whether ViTs can facilitate feature learning in MVS? In this paper, w…
GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；Shanghai Innovation Institute（上海创新研究院）；Chongqing Key Laboratory of Precision Optics, Chongqing Institute of East China Normal University（重庆精密光学重点实验室，东华大学重庆研究院）；Shanghai Key Laboratory of Computer Software Evaluating and Testing（上海计算机软件评测测试重点实验室）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程学院）
Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection
ZongmuTech（宗目科技）；Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学脑智能科学与技术研究院）；Huazhong University of Science and Technology（华中科技大学）
UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views
CUHK T Stone Robotics Institute（香港中文大学T Stone机器人研究所）；The Chinese University of Hong Kong（香港中文大学）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Tencent AI Lab（腾讯AI实验室）；Hong Kong Center for Logistics Robotics（香港物流机器人中心）
