Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information from LiDAR to image-based network. However, modality gap between image and LiDAR seriously limits its accuracy. In this paper, we systematically investigate the negative transfer problem induced by modality gap in cross-modality distillation for the first time, including not only the architecture inconsistency issue but more importantly the feature overfitting issue. We propose a selective learning approach named MonoSTL to overcome these issues, which encourages positive transfer of depth information from LiDAR while alleviates the negative transfer on image-based network. On the one hand, we utilize similar architectures to ensure spatial alignment of features between image-based and LiDAR-based networks. On the other hand, we develop two novel distillation modules, namely Depth-Aware Selective Feature Distillation (DASFD) and Depth-Aware Selective Relation Distillation (DASRD), which selectively learn positive features and relationships of objects by integrating depth uncertainty into feature and relation distillations, respectively. Our approach can be seamlessly integrated into various CNN-based and DETR-based models, where we take three recent models on KITTI and a recent model on NuScenes for validation. Extensive experiments show that our approach considerably improves the accuracy of the base models and thereby achieves the best accuracy compared with all recently released SOTA models.
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and insufficiently leverage the LiDAR information, where the rich potential of the LiDAR data has not been well exploited. In this paper, we propose the Cross-Modality Knowledge Distillation (CMKD) network for monocular 3D detection to efficiently and directly transfer the knowledge from LiDAR modality to image modality on both features and responses. Moreover, we…
Handong Global University（韩东国际大学）；Sungkyunkwan University（成均馆大学）；Institute for Basic Science（基础科学研究院）
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently …
Today's state-of-the-art methods for 3D object detection are based on lidar, stereo, or monocular cameras. Lidar-based methods achieve the best accuracy, but have a large footprint, high cost, and mechanically-limited angular sampling rates, resulting in low spatial resolution at long ranges. Recent approaches based on low-cost monocular or stereo cameras promise to overcome these limitations but struggle in low-light or low-contrast regions as they rely on passive CMOS sensors. In this work, we propose a novel 3D object detection modality that exploits temporal illumination cues from a low-co…
MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders
S-Lab, Nanyang Technological University（新加坡南洋理工大学S-Lab）；College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；University of Chinese Academy of Sciences（中国科学院大学）
Quality-aware Selective Fusion Network for V-D-T Salient Object Detection
School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）；School of Software, Shandong University（山东大学软件学院）；Lishui Institute of Hangzhou Dianzi University（杭州电子科技大学丽水研究院）；School of Communication Engineering, Hangzhou Dianzi University（杭州电子科技大学通信工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapters
School of Information and Electronics, Beijing Institute of Technology（信息与电子学院，北京理工大学）；Beijing Institute of Technology Chongqing Innovation Center（北京理工大学重庆创新中心）；National Key Laboratory for Space-Born Intelligent Information Processing（空间智能信息处理国家级重点实验室）；School of Automation, Beijing Institute of Technology（自动化学院，北京理工大学）
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Northwestern Polytechnical University（西北工业大学）；Inception Institute of Artificial Intelligence（因塞普申人工智能研究院）
How to effectively fuse cross-modal information is the key problem for RGB-D salient object detection. Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss. Many models use the feature fusion strategy but are limited by the low-order point-to-point fusion methods. In this paper, we propose a novel mutual attention model by fusing attention and contexts from different modalities. We use the non-local attention of one modality to propagate long-range contextual depen…
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…
Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection
Xidian University（西安电子科技大学）；Nanyang Technological University（南洋理工大学）；Zhengzhou University（郑州大学）；China University of Geosciences（中国地质大学）；Swinburne University of Technology（斯威本科技大学）
LISMARS；Hubei Luojia Laboratory（湖北珞珈实验室）；Wuhan University（武汉大学）；The University of Hong Kong（香港大学）；The Hong Kong Polytechnic University（香港理工大学）；Texas A&M University（德克萨斯农工大学）
TUNI: Unifying Pre-training and Fine-tuning with Modality-Aware Mutual Learning and Rectification for RGB-T Semantic Segmentation
School of Automation, Beijing Institute of Technology（自动化学院，北京理工大学）；School of Computer Science, Wuhan University（计算机学院，武汉大学）；Great Wall Motor（长城汽车）；School of Information and Electronic Engineering, Zhejiang University of Science and Technology（信息电子工程学院，浙江理工大学）
National Yang Ming Chiao Tung University（阳明交通大学）；University of Washington（华盛顿大学）
This paper introduces a novel human pose estimation benchmark, Human Pose with Millimeter Wave Radar (HuPR), that includes synchronized vision and radio signal components. This dataset is created using cross-calibrated mmWave radar sensors and a monocular RGB camera for cross-modality training of radar-based human pose estimation. There are two advantages of using mmWave radar to perform human pose estimation. First, it is robust to dark and low-light conditions. Second, it is not visually perceivable by humans and thus, can be widely applied to applications with privacy concerns, e.g., survei…
We introduce a discriminative multimodal descriptor based on a pair of sensor readings: a point cloud from a LiDAR and an image from an RGB camera. Our descriptor, named MinkLoc++, can be used for place recognition, re-localization and loop closure purposes in robotics or autonomous vehicles applications. We use late fusion approach, where each modality is processed separately and fused in the final part of the processing pipeline. The proposed method achieves state-of-the-art performance on standard place recognition benchmarks. We also identify dominating modality problem when training a mul…
EGM-Det: Entropy-Guided Multimodal Adaptive Fusion for UAV RGB-IR Object Detection
School of Cybersecurity, Northwestern Polytechnical University（西北工业大学网络空间安全学院）；School of Automation and Software Engineering, Shanxi University（山西大学自动化与软件学院）
RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Images
Zhongnan University of Economics and Law（中南财经政法大学）；City University of Macau（澳门城市大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Hubei University（湖北大学）；Xi’an High-tech Research Institute（西安高新技术研究所）；China University of Geosciences (Wuhan)（中国地质大学（武汉））
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；École Polytechnique（巴黎综合理工学院）；Technical University of Munich（慕尼黑工业大学）
Learning-based depth estimation has witnessed recent progress in multiple directions; from self-supervision using monocular video to supervised methods offering highest accuracy. Complementary to supervision, further boosts to performance and robustness are gained by combining information from multiple signals. In this paper we systematically investigate key trade-offs associated with sensor and modality design choices as well as related model training strategies. Our study leads us to a new method, capable of connecting modality-specific advantages from polarisation, Time-of-Flight and struct…
University of New South Wales（新南威尔士大学）；Griffith University（格里菲斯大学）；South China University of Technology（华南理工大学）；University of Technology Sydney（悉尼科技大学）
Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment. However, most existing work in this field employs domain-specific approaches and is thus ineffective in complex sit- uations where multi-modality sensor data are col- lected. Moreover, the wearable sensor data are less informative than the conventional data such as texts or images. In this paper, to improve the adapt- ability of such classification methods across differ- ent application domains, we turn this classific…
We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while pr…
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, especially in weak texture regions and at object boundaries. To overcome this weakness, we propose novel ideas to improve self-supervised monocular depth estimation by leveraging cross-domain information, especially scene semantics. We focus on incorporating implicit semantic knowledge into geometric representation enhancement and suggest two ideas: a metric learning approach that…
Sun Yat-sen University（中山大学）；NEC Laboratories America（美国 NEC 实验室）；National Chiao Tung University（国立交通大学）
Deep networks for Monocular Depth Estimation (MDE) have achieved promising performance recently and it is of great importance to further understand the interpretability of these networks. Existing methods attempt to provide posthoc explanations by investigating visual cues, which may not explore the internal representations learned by deep networks. In this paper, we find that some hidden units of the network are selective to certain ranges of depth, and thus such behavior can be served as a way to interpret the internal representations. Based on our observations, we quantify the interpretabil…
Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO\&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using direct 2D-3D line correspondences. To handle the appearance differences and modality gaps between LiDAR point clouds and images, geometric 3D lines are extracted offline from LiDAR maps while robust 2D lines are …
Computer vision-based object detection is a key modality for advanced Detect-And-Avoid systems that allow for autonomous flight missions of UAVs. While standard object detection frameworks do not predict the actual depth of an object, this information is crucial to avoid collisions. In this paper, we propose several novel extensions to state-of-the-art methods for monocular object detection from images at long range. Firstly, we propose Sigmoid and ReLU-like encodings when modeling depth estimation as a regression task. Secondly, we frame the depth estimation as a classification problem and in…
Korea Electronics Technology Institute (KETI)（韩国电子技术研究院（KETI））
We present an approach to generating 3D human models from images. The key to our framework is that we predict double-sided orthographic depth maps and color images from a single perspective projected image. Our framework consists of three networks. The first network predicts normal maps to recover geometric details such as wrinkles in the clothes and facial regions. The second network predicts shade-removed images for the front and back views by utilizing the predicted normal maps. The last multi-headed network takes both normal maps and shade-free images and predicts depth maps while selectiv…
The exploration of mutual-benefit cross-domains has shown great potential toward accurate self-supervised depth estimation. In this work, we revisit feature fusion between depth and semantic information and propose an efficient local adaptive attention method for geometric aware representation enhancement. Instead of building global connections or deforming attention across the feature space without restraint, we bound the spatial interaction within a learnable region of interest. In particular, we leverage geometric cues from semantic information to learn local adaptive bounding boxes to guid…
We focus on estimating the 3D orientation of the ground plane from a single image. We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and depth estimates. Specifically, our proposed model, GroundNet, first estimates the depth and surface normal in two separate streams, from which two ground plane normals are then computed deterministically. To leverage the geometric correlation between depth and normal, we propose to add a consistency loss on top of the computed ground plane normal…
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and training strategy for monocular depth estimation to further improve the prediction accuracy of the network. We deploy a hierarchical transformer encoder to capture and convey the global context, and design a lightweight yet powerful decoder to generate an estimated depth map while considering local connectivity. By constructing connected paths between multi…
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
Harbin Engineering University（哈尔滨工程大学）；Key Laboratory of Advanced Marine Communication and Information Technology（先进海洋通信与信息技术重点实验室）；University of Toronto（多伦多大学）；Kanagawa University（神奈川大学）
BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
Laboratory Of Intelligent Collaborative Computing, University of Electronic Science and Technology of China（电子科技大学智能协同计算实验室）；Xinjiang University（新疆大学）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
University of Electronic Science and Technology of China（电子科技大学）；Intelligent Digital Media Technology Key Laboratory of Sichuan Province（四川省智能数字媒体技术重点实验室）
Self-supervised methods play an increasingly important role in monocular depth estimation due to their great potential and low annotation cost. To close the gap with supervised methods, recent works take advantage of extra constraints, e.g., semantic segmentation. However, these methods will inevitably increase the burden on the model. In this paper, we show theoretical and empirical evidence that the potential capacity of self-supervised monocular depth estimation can be excavated without increasing this cost. In particular, we propose (1) a novel data augmentation approach called data grafti…
