PyTorchKR Papers

“Object Detection”

총 13,453편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2112.01838공식 코드 · Papers with Code

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

Recent developments in transformer models for visual data have led to significant improvements in recognition and detection tasks. In particular, using learnable queries in place of region proposals has given rise to a new class of one-stage detection models, spearheaded by the Detection Transformer (DETR). Variations on this one-stage approach have since dominated human-object interaction (HOI) detection. However, the success of such one-stage HOI detectors can largely be attributed to the representation power of transformers. We discovered that when equipped with the same transformer, their two-stage counterparts can be more performant and memory-efficient, while taking a fraction of the time to train. In this work, we propose the Unary-Pairwise Transformer, a two-stage detector that exploits unary and pairwise representations for HOIs. We observe that the unary and pairwise parts of our transformer network specialise, with the former preferentially increasing the scores of positive examples and the latter decreasing the scores of negative examples. We evaluate our method on the HICO-DET and V-COCO datasets, and significantly outperform state-of-the-art approaches. At inference time, our model with ResNet50 approaches real-time performance on a single GPU.

arXiv:2406.03095공식 코드 · Papers with Code

EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos

Surgical tool detection is a fundamental task for understanding egocentric open surgery videos. However, detecting surgical tools presents significant challenges due to their highly imbalanced class distribution, similar shapes and similar textures, and heavy occlusion. The lack of a comprehensive large-scale dataset compounds these challenges. In this paper, we introduce EgoSurgery-Tool, an extension of the existing EgoSurgery-Phase dataset, which contains real open surgery videos captured using an egocentric camera attached to the surgeon's head, along with phase annotations. EgoSurgery-Tool has been densely annotated with surgical tools and comprises over 49K surgical tool bounding boxes across 15 categories, constituting a large-scale surgical tool detection dataset. EgoSurgery-Tool also provides annotations for hand detection with over 46K hand-bounding boxes, capturing hand-object interactions that are crucial for understanding activities in egocentric open surgery. EgoSurgery-Tool is superior to existing datasets due to its larger scale, greater variety of surgical tools, more annotations, and denser scenes. We conduct a comprehensive analysis of EgoSurgery-Tool using nine popular object detectors to assess their effectiveness in both surgical tool and hand detection. The dataset will be released at https://github.com/Fujiry0/EgoSurgery.

arXiv:2004.07786

Multi-Object Tracking with Siamese Track-RCNN

Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these separate components and makes a final prediction. Differently, this work aims to unify all these in a single tracking system. Towards this, we propose Siamese Track-RCNN, a two stage detect-and-track framework which consists of three functional branches: (1) the detection branch localizes object instances; (2) the Siamese-based track branch estimates the object motion and (3) the object re-identification branch re-activates the previously terminated tracks when they re-emerge. We test our tracking system on two popular datasets of the MOTChallenge. Siamese Track-RCNN achieves significantly higher results than the state-of-the-art, while also being much more efficient, thanks to its unified design.

arXiv:2110.13713공식 코드 · Papers with Code

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2x0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.

arXiv:2303.12776공식 코드 · Papers with Code

Dense Distinct Query for End-to-End Object Detection

One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries cannot guarantee a high recall, while dense queries inevitably bring more similar queries and encounter optimization difficulties. As both sparse and dense queries are problematic, then what are the expected queries in end-to-end object detection? This paper shows that the solution should be Dense Distinct Queries (DDQ). Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments. DDQ blends the advantages of traditional and recent end-to-end detectors and significantly improves the performance of various detectors including FCN, R-CNN, and DETRs. Most impressively, DDQ-DETR achieves 52.1 AP on MS-COCO dataset within 12 epochs using a ResNet-50 backbone, outperforming all existing detectors in the same setting. DDQ also shares the benefit of end-to-end detectors in crowded scenes and achieves 93.8 AP on CrowdHuman. We hope DDQ can inspire researchers to consider the complementarity between traditional methods and end-to-end detectors. The source code can be found at \url{https://github.com/jshilong/DDQ}.

arXiv:2012.11704

HDNET: Exploiting HD Maps for 3D Object Detection

In this paper we show that High-Definition (HD) maps provide strong priors that can boost the performance and robustness of modern 3D object detectors. Towards this goal, we design a single stage detector that extracts geometric and semantic features from the HD maps. As maps might not be available everywhere, we also propose a map prediction module that estimates the map on the fly from raw LiDAR data. We conduct extensive experiments on KITTI as well as a large-scale 3D detection benchmark containing 1 million frames, and show that the proposed map-aware detector consistently outperforms the state-of-the-art in both mapped and un-mapped scenarios. Importantly the whole framework runs at 20 frames per second.

arXiv:1811.04533

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multi-scale, pyramidal architecture of the backbones which are actually designed for object classification task. Newly, in this work, we present a method called Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. First, we fuse multi-level features (i.e. multiple layers) extracted by backbone as the base feature. Second, we feed the base feature into a block of alternating joint Thinned U-shape Modules and Feature Fusion Modules and exploit the decoder layers of each u-shape module as the features for detecting objects. Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels. To evaluate the effectiveness of the proposed MLFPN, we design and train a powerful end-to-end one-stage object detector we call M2Det by integrating it into the architecture of SSD, which gets better detection performance than state-of-the-art one-stage detectors. Specifically, on MS-COCO benchmark, M2Det achieves AP of 41.0 at speed of 11.8 FPS with single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which is the new state-of-the-art results among one-stage detectors. The code will be made available on \url{https://github.com/qijiezhao/M2Det.

arXiv:1906.01891

Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks

Finding automatically multiple lesions in large images is a common problem in medical image analysis. Solving this problem can be challenging if, during optimization, the automated method cannot access information about the location of the lesions nor is given single examples of the lesions. We propose a new weakly supervised detection method using neural networks, that computes attention maps revealing the locations of brain lesions. These attention maps are computed using the last feature maps of a segmentation network optimized only with global image-level labels. The proposed method can generate attention maps at full input resolution without need for interpolation during preprocessing, which allows small lesions to appear in attention maps. For comparison, we modify state-of-the-art methods to compute attention maps for weakly supervised object detection, by using a global regression objective instead of the more conventional classification objective. This regression objective optimizes the number of occurrences of the target object in an image, e.g. the number of brain lesions in a scan, or the number of digits in an image. We study the behavior of the proposed method in MNIST-based detection datasets, and evaluate it for the challenging detection of enlarged perivascular spaces - a type of brain lesion - in a dataset of 2202 3D scans with point-wise annotations in the center of all lesions in four brain regions. In the brain dataset, the weakly supervised detection methods come close to the human intrarater agreement in each region. The proposed method reaches the best area under the curve in two out of four regions, and has the lowest number of false positive detections in all regions, while its average sensitivity over all regions is similar to that of the other best methods. The proposed method can facilitate epidemiological and clinical studies of enlarged perivascular spaces.

arXiv:2608.29510v1cs.CV

ARMOR: 데이터 희소성 환경에서 적대적으로 강건한 항공 객체 검출을 위한 매니폴드 지향 학습

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity

항공 객체 검출(aerial object detection)은 실제 환경에 점차 널리 배포되고 있으나, 모델은 객체를 감지하지 못하게 만드는 물리적이고 유니버설(universal)한 적대적 패치(adversarial patch)에 여전히 취약합니다. 나아가 방어자는 학습 데이터 희소성이라는 실질적인 제약에 직면합니다. 항공 영상은 수집과 라벨링 비용이 높아, 배포 현장에서는 적대적 강건성(adversarial robustness) 벤치마크가 가정하는 수만 장의 이미지 대신 대개 수백 장 정도만 확보할 수 있기 때문입니다. 모델 취약성과 학습 데이터 희소성 문제를 해결하기 위해, 본 논문에서는 적은 데이터 환경에서 온-매니폴드 적대적 학습(on-manifold adversarial training, OMAT)의 핵심 통찰을 실현하는 새로운 방어 기법인 ARMOR(Adversarial Robustness with Manifold-Oriented Training)를 제안합니다. ARMOR는 데이터 매니폴드(데이터의 유의미한 특징을 포착하는 조밀한 구조)를 모델링하여 학습 과정에서 이러한 특징을 학습하고 견고하게 만든다는 OMAT의 통찰을 기반으로 합니다. 기존 OMAT이 이를 달성하기 위해 대규모 생성 모델 학습 및 적대적 학습과 같은 데이터 집약적 연산에 의존하는 반면, ARMOR는 검출 태스크에서 이미 제공하는 라벨을 재사용하는 데이터 효율적인 접근 방식을 채택합니다. 구체적으로 ARMOR는 (i) 이미지 배경을 마스킹하여 객체 관련 특징을 보존하고, (ii) 객체 위에 무작위 패치를 주입하여 특징 강건성을 향상시킵니다. 물리적으로 구현 가능한 적대적 패치를 활용한 저데이터 실험을 통해 쿼리가 필요 없는 전이 공격(query-free transfer attack)과 방어 인지 공격(defense-aware attack)을 모두 평가했습니다. ARMOR는 0.90 이상의 높은 정상(clean) 성능 모델 신뢰도를 유지하는 동시에, 최첨단(SOTA) 방어 기법 대비 적대적 강건성을 모델 신뢰도 기준 최대 0.32 향상시켰습니다. 출력된 패치를 사용한 물리적 실험을 통해 이러한 성능 향상이 실제 배포 환경에서도 유지됨을 확인했습니다. 전반적으로 ARMOR는 매니폴드 기반 학습의 통찰을 활용하여 학습 데이터가 부족한 환경에서도 객체 검출기를 방어합니다.

arXiv:2201.03176공식 코드 · Papers with Code

Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond

Pedestrian detection is the cornerstone of many vision based applications, starting from object tracking to video surveillance and more recently, autonomous driving. With the rapid development of deep learning in object detection, pedestrian detection has achieved very good performance in traditional single-dataset training and evaluation setting. However, in this study on generalizable pedestrian detectors, we show that, current pedestrian detectors poorly handle even small domain shifts in cross-dataset evaluation. We attribute the limited generalization to two main factors, the method and the current sources of data. Regarding the method, we illustrate that biasness present in the design choices (e.g anchor settings) of current pedestrian detectors are the main contributing factor to the limited generalization. Most modern pedestrian detectors are tailored towards target dataset, where they do achieve high performance in traditional single training and testing pipeline, but suffer a degrade in performance when evaluated through cross-dataset evaluation. Consequently, a general object detector performs better in cross-dataset evaluation compared with state of the art pedestrian detectors, due to its generic design. As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians. Therefore, benchmarks curated by crawling the web (which contain diverse and dense scenarios), are an efficient source of pre-training for providing a more robust representation. Accordingly, we propose a progressive fine-tuning strategy which improves generalization. Code and models can accessed at https://github.com/hasanirtiza/Pedestron.

arXiv:2303.13561

MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation

Monocular 3D object detection (Mono3D) in mobile settings (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Due to the near-far disparity phenomenon of monocular vision and the ever-changing camera pose, it is hard to acquire high detection accuracy, especially for far objects. Inspired by the insight that the depth of an object can be well determined according to the depth of the ground where it stands, in this paper, we propose a novel Mono3D framework, called MoGDE, which constantly estimates the corresponding ground depth of an image and then utilizes the estimated ground depth information to guide Mono3D. To this end, we utilize a pose detection network to estimate the pose of the camera and then construct a feature map portraying pixel-level ground depth according to the 3D-to-2D perspective geometry. Moreover, to improve Mono3D with the estimated ground depth, we design an RGB-D feature fusion network based on the transformer structure, where the long-range self-attention mechanism is utilized to effectively identify ground-contacting points and pin the corresponding ground depth to the image feature map. We conduct extensive experiments on the real-world KITTI dataset. The results demonstrate that MoGDE can effectively improve the Mono3D accuracy and robustness for both near and far objects. MoGDE yields the best performance compared with the state-of-the-art methods by a large margin and is ranked number one on the KITTI 3D benchmark.

arXiv:1903.09126

Progressive Sparse Local Attention for Video object detection

Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed.

arXiv:2105.11111공식 코드 · Papers with Code

Oriented RepPoints for Aerial Object Detection

In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings. Unlike the mainstreamed approaches regressing the bounding box orientations, this paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances. To this end, three oriented conversion functions are presented to facilitate the classification and localization with accurate orientation. Moreover, we propose an effective quality assessment and sample assignment scheme for adaptive points learning toward choosing the representative oriented reppoints samples during training, which is able to capture the non-axis aligned features from adjacent objects or background noises. A spatial constraint is introduced to penalize the outlier points for roust adaptive learning. Experimental results on four challenging aerial datasets including DOTA, HRSC2016, UCAS-AOD and DIOR-R, demonstrate the efficacy of our proposed approach. The source code is availabel at: https://github.com/LiWentomng/OrientedRepPoints.

arXiv:2402.13578공식 코드 · Papers with Code

TransGOP: Transformer-Based Gaze Object Prediction

Gaze object prediction aims to predict the location and category of the object that is watched by a human. Previous gaze object prediction works use CNN-based object detectors to predict the object's location. However, we find that Transformer-based object detectors can predict more accurate object location for dense objects in retail scenarios. Moreover, the long-distance modeling capability of the Transformer can help to build relationships between the human head and the gaze object, which is important for the GOP task. To this end, this paper introduces Transformer into the fields of gaze object prediction and proposes an end-to-end Transformer-based gaze object prediction method named TransGOP. Specifically, TransGOP uses an off-the-shelf Transformer-based object detector to detect the location of objects and designs a Transformer-based gaze autoencoder in the gaze regressor to establish long-distance gaze relationships. Moreover, to improve gaze heatmap regression, we propose an object-to-gaze cross-attention mechanism to let the queries of the gaze autoencoder learn the global-memory position knowledge from the object detector. Finally, to make the whole framework end-to-end trained, we propose a Gaze Box loss to jointly optimize the object detector and gaze regressor by enhancing the gaze heatmap energy in the box of the gaze object. Extensive experiments on the GOO-Synth and GOO-Real datasets demonstrate that our TransGOP achieves state-of-the-art performance on all tracks, i.e., object detection, gaze estimation, and gaze object prediction. Our code will be available at https://github.com/chenxi-Guo/TransGOP.git.

arXiv:2202.04231공식 코드 · Papers with Code

Real-Time Event-Based Tracking and Detection for Maritime Environments

Event cameras are ideal for object tracking applications due to their ability to capture fast-moving objects while mitigating latency and data redundancy. Existing event-based clustering and feature tracking approaches for surveillance and object detection work well in the majority of cases, but fall short in a maritime environment. Our application of maritime vessel detection and tracking requires a process that can identify features and output a confidence score representing the likelihood that the feature was produced by a vessel, which may trigger a subsequent alert or activate a classification system. However, the maritime environment presents unique challenges such as the tendency of waves to produce the majority of events, demanding the majority of computational processing and producing false positive detections. By filtering redundant events and analyzing the movement of each event cluster, we can identify and track vessels while ignoring shorter lived and erratic features such as those produced by waves.

arXiv:2001.11584

Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion

Images of heavily occluded objects in cluttered scenes, such as fruit clusters in trees, are hard to segment. To further retrieve the 3D size and 6D pose of each individual object in such cases, bounding boxes are not reliable from multiple views since only a little portion of the object's geometry is captured. We introduce the first CNN-based ellipse detector, called Ellipse R-CNN, to represent and infer occluded objects as ellipses. We first propose a robust and compact ellipse regression based on the Mask R-CNN architecture for elliptical object detection. Our method can infer the parameters of multiple elliptical objects even they are occluded by other neighboring objects. For better occlusion handling, we exploit refined feature regions for the regression stage, and integrate the U-Net structure for learning different occlusion patterns to compute the final detection score. The correctness of ellipse regression is validated through experiments performed on synthetic data of clustered ellipses. We further quantitatively and qualitatively demonstrate that our approach outperforms the state-of-the-art model (i.e., Mask R-CNN followed by ellipse fitting) and its three variants on both synthetic and real datasets of occluded and clustered elliptical objects.

arXiv:2010.08243공식 코드 · Papers with Code

SF-UDA$^{3D}$: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection

3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e.g., point density variations). This paper proposes SF-UDA$^{3D}$, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN 3D detector to target domains for which we have no annotations (unsupervised), neither we hold images nor annotations of the source domain (source-free). SF-UDA$^{3D}$ is novel on both aspects. Our approach is based on pseudo-annotations, reversible scale-transformations and motion coherency. SF-UDA$^{3D}$ outperforms both previous domain adaptation techniques based on features alignment and state-of-the-art 3D object detection methods which additionally use few-shot target annotations or target annotation statistics. This is demonstrated by extensive experiments on two large-scale datasets, i.e., KITTI and nuScenes.

arXiv:1806.04331

Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks

Ship detection has been playing a significant role in the field of remote sensing for a long time but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection and the redundancy of detection region. In order to solve such problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ship in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving the problem resulted from the narrow width of the ship. Compared with previous multi-scale detectors such as Feature Pyramid Network (FPN), DFPN builds the high-level semantic feature-maps for all scales by means of dense connections, through which enhances the feature propagation and encourages the feature reuse. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multi-scale ROI Align for the purpose of maintaining the completeness of semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on R-DFPN representation has a state-of-the-art performance.

arXiv:1808.09023

Real-time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy

Vehicle-to-Pedestrian (V2P) communication can significantly improve pedestrian safety at a signalized intersection. It is unlikely that pedestrians will carry a low latency communication enabled device and activate a pedestrian safety application in their hand-held device all the time. Because of this limitation, multiple traffic cameras at the signalized intersection can be used to accurately detect and locate pedestrians using deep learning and broadcast safety alerts related to pedestrians to warn connected and automated vehicles around a signalized intersection. However, unavailability of high-performance computing infrastructure at the roadside and limited network bandwidth between traffic cameras and the computing infrastructure limits the ability of real-time data streaming and processing for pedestrian detection. In this paper, we develop an edge computing based real-time pedestrian detection strategy combining pedestrian detection algorithm using deep learning and an efficient data communication approach to reduce bandwidth requirements while maintaining a high object detection accuracy. We utilize a lossy compression technique on traffic camera data to determine the tradeoff between the reduction of the communication bandwidth requirements and a defined object detection accuracy. The performance of the pedestrian-detection strategy is measured in terms of pedestrian classification accuracy with varying peak signal-to-noise ratios. The analyses reveal that we detect pedestrians by maintaining a defined detection accuracy with a peak signal-to-noise ratio (PSNR) 43 dB while reducing the communication bandwidth from 9.82 Mbits/sec to 0.31 Mbits/sec, a 31x reduction.

arXiv:2211.07108

Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations

Heavily relying on 3D annotations limits the real-world application of 3D object detection. In this paper, we propose a method that does not demand any 3D annotation, while being able to predict fully oriented 3D bounding boxes. Our method, called Recursive Cross-View (RCV), utilizes the three-view principle to convert 3D detection into multiple 2D detection tasks, requiring only a subset of 2D labels. We propose a recursive paradigm, in which instance segmentation and 3D bounding box generation by Cross-View are implemented recursively until convergence. Specifically, our proposed method involves the use of a frustum for each 2D bounding box, which is then followed by the recursive paradigm that ultimately generates a fully oriented 3D box, along with its corresponding class and score. Note that, class and score are given by the 2D detector. Estimated on the SUN RGB-D and KITTI datasets, our method outperforms existing image-based approaches. To justify that our method can be quickly used to new tasks, we implement it on two real-world scenarios, namely 3D human detection and 3D hand detection. As a result, two new 3D annotated datasets are obtained, which means that RCV can be viewed as a (semi-) automatic 3D annotator. Furthermore, we deploy RCV on a depth sensor, which achieves detection at 7 fps on a live RGB-D stream. RCV is the first 3D detection method that yields fully oriented 3D boxes without consuming 3D labels.