Conventional 2D pose estimation models are constrained by their design to specific object categories. This limits their applicability to predefined objects. To overcome these limitations, category-agnostic pose estimation (CAPE) emerged as a solution. CAPE aims to facilitate keypoint localization for diverse object categories using a unified model, which can generalize from minimal annotated support images. Recent CAPE works have produced object poses based on arbitrary keypoint definitions annotated on a user-provided support image. Our work departs from conventional CAPE methods, which require a support image, by adopting a text-based approach instead of the support image. Specifically, we use a pose-graph, where nodes represent keypoints that are described with text. This representation takes advantage of the abstraction of text descriptions and the structure imposed by the graph. Our approach effectively breaks symmetry, preserves structure, and improves occlusion handling. We validate our novel approach using the MP-100 benchmark, a comprehensive dataset spanning over 100 categories and 18,000 images. Under a 1-shot setting, our solution achieves a notable performance boost of 1.07\%, establishing a new state-of-the-art for CAPE. Additionally, we enrich the dataset by providing text description annotations, further enhancing its utility for future research.
Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories. This restriction becomes particularly challenging when dealing with novel objects due to the lack of relevant training data. To address this limitation, category-agnostic pose estimation (CAPE) was introduced. CAPE aims to enable keypoint localization for arbitrary object categories using a few-shot single model, requiring minimal support images with annotated keypoints. We present a significant departure from conventional CAPE techniques, which treat keypoints as isolated entities, by treating the input pose data as a graph. We leverage the inherent geometrical relations between keypoints through a graph-based network to break symmetry, preserve structure, and better handle occlusions. We validate our approach on the MP-100 benchmark, a comprehensive dataset comprising over 20,000 images spanning over 100 categories. Our solution boosts performance by 0.98% under a 1-shot setting, achieving a new state-of-the-art for CAPE. Additionally, we enhance the dataset with skeleton annotations. Our code and data are publicly available.
Vehicle pose estimation with LiDAR is essential in the perception technology of autonomous driving. However, due to incomplete observation measurements and sparsity of the LiDAR point cloud, it is challenging to achieve satisfactory pose extraction based on 3D LiDAR with the existing pose estimation methods. In addition, the demand for real-time performance further increases the difficulty of the pose estimation task. In this paper, we propose a novel vehicle pose estimation method based on the convex hull. The extracted 3D cluster is reduced to the convex hull, reducing the subsequent computation burden while preserving essential contour information. Subsequently, a novel criterion based on the minimum occlusion area is developed for the search-based algorithm, enabling accurate pose estimation. Additionally, this criterion renders the proposed algorithm particularly well-suited for obstacle avoidance. The proposed algorithm is validated on the KITTI dataset and a manually labeled dataset acquired at an industrial park. The results demonstrate that our proposed method can achieve better accuracy than the classical pose estimation method while maintaining real-time speed.
We consider a category-level perception problem, where one is given 2D or 3D sensor data picturing an object of a given category (e.g., a car), and has to reconstruct the 3D pose and shape of the object despite intra-class variability (i.e., different car models have different shapes). We consider an active shape model, where -- for an object category -- we are given a library of potential CAD models describing objects in that category, and we adopt a standard formulation where pose and shape are estimated from 2D or 3D keypoints via non-convex optimization. Our first contribution is to develop PACE3D* and PACE2D*, the first certifiably optimal solvers for pose and shape estimation using 3D and 2D keypoints, respectively. Both solvers rely on the design of tight (i.e., exact) semidefinite relaxations. Our second contribution is to develop outlier-robust versions of both solvers, named PACE3D# and PACE2D#. Towards this goal, we propose ROBIN, a general graph-theoretic framework to prune outliers, which uses compatibility hypergraphs to model measurements' compatibility. We show that in category-level perception problems these hypergraphs can be built from the winding orders of the keypoints (in 2D) or their convex hulls (in 3D), and many outliers can be filtered out via maximum hyperclique computation. The last contribution is an extensive experimental evaluation. Besides providing an ablation study on simulated datasets and on the PASCAL3D+ dataset, we combine our solver with a deep keypoint detector, and show that PACE3D# improves over the state of the art in vehicle pose estimation in the ApolloScape datasets, and its runtime is compatible with practical applications. We release our code at https://github.com/MIT-SPARK/PACE.
We present a new learning-based framework to recover vehicle pose in SO(3) from a single RGB image. In contrast to previous works that map from local appearance to observation angles, we explore a progressive approach by extracting meaningful Intermediate Geometrical Representations (IGRs) to estimate egocentric vehicle orientation. This approach features a deep model that transforms perceived intensities to IGRs, which are mapped to a 3D representation encoding object orientation in the camera coordinate system. Core problems are what IGRs to use and how to learn them more effectively. We answer the former question by designing IGRs based on an interpolated cuboid that derives from primitive 3D annotation readily. The latter question motivates us to incorporate geometry knowledge with a new loss function based on a projective invariant. This loss function allows unlabeled data to be used in the training stage to improve representation learning. Without additional labels, our system outperforms previous monocular RGB-based methods for joint vehicle detection and pose estimation on the KITTI benchmark, achieving performance even comparable to stereo methods. Code and pre-trained models are available at this https URL.
We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass. Extensive experiments show that our diverse feature extraction and fusion scheme can greatly improve model performance. Based on a divide-and-conquer 3D shape representation strategy, GSNet reconstructs 3D vehicle shape with great detail (1352 vertices and 2700 faces). This dense mesh representation further leads us to consider geometrical consistency and scene context, and inspires a new multi-objective loss function to regularize network training, which in turn improves the accuracy of 6D pose estimation and validates the merit of jointly performing both tasks. We evaluate GSNet on the largest multi-task ApolloCar3D benchmark and achieve state-of-the-art performance both quantitatively and qualitatively. Project page is available at https://lkeab.github.io/gsnet/.
In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, we propose to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes our system more widely applicable. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods. It is caused by the way to form representation for the prediction in 3D scenarios. Our method, called Deep Stereo Geometry Network (DSGN), significantly reduces this gap by detecting 3D objects on a differentiable volumetric representation -- 3D geometric volume, which effectively encodes 3D geometric structure for 3D regular space. With this representation, we learn depth information and semantic cues simultaneously. For the first time, we provide a simple and effective one-stage stereo-based 3D detection pipeline that jointly estimates the depth and detects 3D objects in an end-to-end learning manner. Our approach outperforms previous stereo-based 3D detectors (about 10 higher in terms of AP) and even achieves comparable performance with several LiDAR-based methods on the KITTI 3D object detection leaderboard. Our code is publicly available at https://github.com/chenyilun95/DSGN.
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without the need for external networks or supervision data. Our method is the first real-time system for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark. Code will be released at https://github.com/Banconxuan/RTM3D.
3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale information, which are vital for 3D object detection. To better represent 3D structure, prior arts typically transform depth maps estimated from 2D images into a pseudo-LiDAR representation, and then apply existing 3D point-cloud based object detectors. However, their results depend heavily on the accuracy of the estimated depth maps, resulting in suboptimal performance. In this work, instead of using pseudo-LiDAR representation, we improve the fundamental 2D fully convolutions by proposing a new local convolutional network (LCN), termed Depth-guided Dynamic-Depthwise-Dilated LCN (D$^4$LCN), where the filters and their receptive fields can be automatically learned from image-based depth maps, making different pixels of different images have different filters. D$^4$LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation. Extensive experiments show that D$^4$LCN outperforms existing works by large margins. For example, the relative improvement of D$^4$LCN against the state-of-the-art on KITTI is 9.1\% in the moderate setting. The code is available at https://github.com/dingmyu/D4LCN.
Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced performance. We propose to reduce the gap by reformulating the monocular 3D detection problem as a standalone 3D region proposal network. We leverage the geometric relationship of 2D and 3D perspectives, allowing 3D boxes to utilize well-known and powerful convolutional features generated in the image-space. To help address the strenuous 3D parameter estimations, we further design depth-aware convolutional layers which enable location specific feature development and in consequence improved 3D scene understanding. Compared to prior work in monocular 3D detection, our method consists of only the proposed 3D region proposal network rather than relying on external networks, data, or multiple stages. M3D-RPN is able to significantly improve the performance of both monocular 3D Object Detection and Bird's Eye View tasks within the KITTI urban autonomous driving dataset, while efficiently using a shared multi-class model.
In this paper, we focus on fine-grained recognition of vehicles mainly in traffic surveillance applications. We propose an approach that is orthogonal to recent advancements in fine-grained recognition (automatic part discovery and bilinear pooling). In addition, in contrast to other methods focused on fine-grained recognition of vehicles, we do not limit ourselves to a frontal/rear viewpoint, but allow the vehicles to be seen from any viewpoint. Our approach is based on 3-D bounding boxes built around the vehicles. The bounding box can be automatically constructed from traffic surveillance data. For scenarios where it is not possible to use precise construction, we propose a method for an estimation of the 3-D bounding box. The 3-D bounding box is used to normalize the image viewpoint by "unpacking" the image into a plane. We also propose to randomly alter the color of the image and add a rectangle with random noise to a random position in the image during the training of convolutional neural networks (CNNs). We have collected a large fine-grained vehicle data set BoxCars116k, with 116k images of vehicles from various viewpoints taken by numerous surveillance cameras. We performed a number of experiments, which show that our proposed method significantly improves CNN classification accuracy (the accuracy is increased by up to 12% points and the error is reduced by up to 50% compared with CNNs without the proposed modifications). We also show that our method outperforms the state-of-the-art methods for fine-grained recognition.