Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. This symbolic representation is a high-level abstraction of the real world, which may render the motion prediction model vulnerable to perception errors (e.g., failures in detecting open-vocabulary obstacles) while missing salient information from the scene context (e.g., poor road conditions). An alternative paradigm is end-to-end learning from raw sensors. However, this approach suffers from the lack of interpretability and requires significantly more training resources. In this work, we propose tokenizing the visual world into a compact set of scene elements and then leveraging pre-trained image foundation models and LiDAR neural networks to encode all the scene elements in an open-vocabulary manner. The image foundation model enables our scene tokens to encode the general knowledge of the open world while the LiDAR neural network encodes geometry information. Our proposed representation can efficiently encode the multi-frame multi-modality observations with a few hundred tokens and is compatible with most transformer-based architectures. To evaluate our method, we have augmented Waymo Open Motion Dataset with camera embeddings. Experiments over Waymo Open Motion Dataset show that our approach leads to significant performance improvements over the state-of-the-art.

Widely adopted motion forecasting datasets sub-stitute the observed sensory inputs with higher-level abstractions such as 3D boxes and polylines. These sparse shapes are inferred through annotating the original scenes with perception systems’ predictions. Such intermediate representations tie the quality of the motion forecasting models to the performance of computer vision models. Moreover, the human-designed explicit interfaces between perception and motion forecasting typically pass only a subset of the semantic information present in the original sensory input. To study the effect of these modular approaches, design new paradigms that mitigate these limitations, and accelerate the development of end-to-end motion forecasting models, we augment the Waymo Open Motion Dataset (WOMD) with large-scale, high-quality, diverse LiDAR data for the motion forecasting task.The new augmented dataset (WOMD-LiDAR)1consists of over 100,000 scenes that each spans 20 seconds, consisting of well-synchronized and calibrated high quality LiDAR point clouds captured across a range of urban and suburban geographies. Compared to Waymo Open Dataset (WOD), WOMDLiDAR dataset contains 100× more scenes. Furthermore, we integrate the LiDAR data into the motion forecasting model training and provide a strong baseline. Experiments show that the LiDAR data brings improvement in the motion forecasting task. We hope that WOMD-LiDAR will provide new opportunities for boosting end-to-end motion forecasting models.

2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view NeRF synthesis framework with general image priors from 2D diffusion models. Formulating single-view reconstruction as an image-conditioned 3D generation problem, we optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint. We leverage off-the-shelf vision-language models and introduce a two-section language guidance as conditioning inputs to the diffusion model. This is essentially helpful for improving multiview content coherence as it narrows down the general image prior conditioned on the semantic and visual features of the single-view input image. Additionally, we introduce a geometric loss based on estimated depth maps to regularize the underlying 3D geometry of the NeRF. Experimental results on the DTU MVS dataset show that our method can synthesize novel views with higher quality even compared to existing methods trained on this dataset. We also demonstrate our generalizability in zero-shot NeRF synthesis for in-the-wild images.

Occluded and long-range objects are ubiquitous and challenging for 3D object detection. Point cloud sequence data provide unique opportunities to improve such cases, as an occluded or distant object can be observed from different viewpoints or gets better visibility over time. However, the efficiency and effectiveness in encoding longterm sequence data can still be improved. In this work, we propose MoDAR, using motion forecasting outputs as a type of virtual modality, to augment LiDAR point clouds. The MoDAR modality propagates object information from temporal contexts to a target frame, represented as a set of virtual points, one for each object from a waypoint on a forecasted trajectory. A fused point cloud of both raw sensor points and the virtual points can then be fed to any off-the-shelf point-cloud based 3D object detector. Evaluated on the Waymo Open Dataset, our method significantly improves prior art detectors by using motion forecasting from extra-long sequences (e.g. 18 seconds), achieving new state of the arts, while not adding much computation overhead.

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving. However, manually creating or recreating real-world-like environments is difficult, expensive, and not scalable. Recent generative model techniques have shown promising progress to address such challenges by learning 3D assets using only plentiful 2D images - but still suffer limitations as they leverage either human-curated image datasets or renderings from manually-created synthetic 3D environments. In this paper, we introduce GINA-3D, a generative model that uses real-world driving data from camera and LiDAR sensors to create realistic 3D implicit neural assets of diverse vehicles and pedestrians. Compared to the existing image datasets, the real-world driving setting poses new challenges due to occlusions, lighting-variations and longtail distributions. GINA-3D tackles these challenges by decoupling representation learning and generative modeling into two stages with a learned triplane latent structure, inspired by recent advances in generative modeling of images. To evaluate our approach, we construct a large-scale object-centric dataset containing over 520K images of vehicles and pedestrians from the Waymo Open Dataset, and a new set of 80K images of longtail instances such as construction equipment, garbage trucks, and cable cars. We compare our model with existing approaches and demonstrate that it achieves state-of-the-art performance in quality and diversity for both generated images and geometries.

Closed-set 3D perception models trained on only a predefined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment. In this paper, we present a multi-modal auto labeling pipeline capable of generating amodal 3D bounding boxes and tracklets for training models on open-set categories without 3D human labels. Our pipeline exploits motion cues inherent in point cloud sequences in combination with the freely available 2D image-text pairs to identify and track all traffic participants. Compared to the recent studies in this domain, which can only provide class-agnostic auto labels limited to moving objects, our method can handle both static and moving objects in the unsupervised manner and is able to output open-vocabulary semantic labels thanks to the proposed vision-language knowledge distillation. Experiments on the Waymo Open Dataset show that our approach outperforms the prior work by significant margins on various unsupervised 3D perception tasks.

Lidars are depth measuring sensors widely used in autonomous driving and augmented reality. However, the large volume of data produced by lidars can lead to high costs in data storage and transmission. While lidar data can be represented as two interchangeable representations: 3D point clouds and range images, most previous work focus on compressing the generic 3D point clouds. In this work, we show that directly compressing the range images can leverage the lidar scanning pattern, compared to compressing the unprojected point clouds. We propose a novel datadriven range image compression algorithm, named RIDDLE (Range Image Deep DeLta Encoding). At its core is a deep model that predicts the next pixel value in a raster scanning order, based on contextual laser shots from both the current and past scans (represented as a 4D point cloud of spherical coordinates and time). The deltas between predictions and original values can then be compressed by entropy encoding. Evaluated on the Waymo Open Dataset and KITTI, our method demonstrates significant improvement in the compression rate (under the same distortion) compared to widely used point cloud and range image compression algorithms as well as recent deep methods.

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples. In this paper, we are interested in training a multi-class 3D object detection model, while using these single-class labeled data. We begin by detailing the unique stance of our “Single-Class Supervision” (SCS) setting with respect to related concepts such as partial supervision and semi supervision. Then, based on the case study of training the multi-class version of Range Sparse Net (RSN), we adapt a spectrum of algorithms - from supervised learning to pseudo-labeling - to fully exploit the properties of our SCS setting, and perform extensive ablation studies to identify the most effective algorithm and practice. Empirical experiments on the Waymo Open Dataset show that proper training under SCS can approach or match full supervision training while saving labeling costs.

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely underexplored, such as using machines to automatically generate high-quality 3D labels. Existing 3D object detectors fail to satisfy the high-quality requirement for offboard uses due to the limited input and speed constraints. In this paper, we propose a novel offboard 3D object detection pipeline using point cloud sequence data. Observing that different frames capture complementary views of objects, we design the offboard detector to make use of the temporal points through both multi-frame object detection and novel objectcentric refinement models. Evaluated on the Waymo Open Dataset, our pipeline named 3D Auto Labeling shows significant gains compared to the state-of-the-art onboard detectors and our offboard baselines. Its performance is even on par with human labels verified through a human label study. Further experiments demonstrate the application of auto labels for semi-supervised learning and provide extensive analysis to validate various design choices.

As autonomous driving systems mature, motion forecasting has received increasing attention as a critical requirement for planning. Of particular importance are interactive situations such as merges, unprotected turns, etc., where predicting individual object motion is not sufficient. Joint predictions of multiple objects are required for effective route planning. There has been a critical need for high-quality motion data that is rich in both interactions and annotation to develop motion planning models. In this work, we introduce the most diverse interactive motion dataset to our knowledge, and provide specific labels for interacting objects suitable for developing joint prediction models. With over 100,000 scenes, each 20 seconds long at 10 Hz, our new dataset contains more than 570 hours of unique data over 1750 km of roadways. It was collected by mining for interesting interactions between vehicles, pedestrians, and cyclists across six cities within the United States. We use a high-accuracy 3D auto-labeling system to generate high quality 3D bounding boxes for each road agent, and provide corresponding high definition 3D maps for each scene. Furthermore, we introduce a new set of metrics that provides a comprehensive evaluation of both single agent and joint agent interaction motion forecasting models. Finally, we provide strong baseline models for individual-agent prediction and joint-prediction. We hope that this new large-scale interactive motion dataset will provide new opportunities for advancing motion forecasting models.

In autonomous driving, a LiDAR-based object detector should perform reliably at different geographic locations and under various weather conditions. While recent 3D detection research focuses on improving performance within a single domain, our study reveals that the performance of modern detectors can drop drastically cross-domain. In this paper, we investigate unsupervised domain adaptation (UDA) for LiDAR-based 3D object detection. On the Waymo Domain Adaptation [49] dataset, we identify the deteriorating point cloud quality as the root cause of the performance drop. To address this issue, we present Semantic Point Generation (SPG), a general approach to enhance the reliability of LiDAR detectors against domain shifts. Specifically, SPG generates semantic points at the predicted fore-ground regions and faithfully recovers missing parts of the foreground objects, which are caused by phenomena such as occlusions, low reflectance, or weather interference. By merging the semantic points with the original points, we obtain an augmented point cloud, which can be directly consumed by modern LiDAR-based detectors. To validate the wide applicability of SPG, we experiment with two representative detectors, PointPillars [22] and PV-RCNN [45]. On the UDA task, SPG significantly improves both detectors across all object categories of interest and at all difficulty levels. SPG can also benefit object detection in the original domain. On the Waymo Open Dataset [49] and KITTI [17], SPG improves 3D detection results of these two methods across all categories. Combined with PV-RCNN [45], SPG achieves state-of-the-art 3D detection results on KITTI.

3D object detection is a key module for safety-critical robotics applications such as autonomous driving. For these applications, we care most about how the detections affect the ego-agent’s behavior and safety (the egocentric perspective). Intuitively, we seek more accurate descriptions of object geometry when it’s more likely to interfere with the ego-agent’s motion trajectory. However, current detection metrics, based on box Intersection-over-Union (IoU), are object-centric and aren’t designed to capture the spatio-temporal relationship between objects and the ego-agent. To address this issue, we propose a new egocentric measure to evaluate 3D object detection, namely Support Distance Error (SDE). Our analysis based on SDE reveals that the egocentric detection quality is bounded by the coarse geometry of the bounding boxes. Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours. Our experiments on the large-scale Waymo Open Dataset show that SDE better reflects the impact of detection quality on the ego-agent’s safety compared to IoU; and the estimated contours from StarPoly consistently improve the egocentric detection quality over recent 3D object detectors.

3D object detection has seen quick progress thanks to advances in deep learning on point clouds. A few recent works have even shown state-of-the-art performance with just point clouds input (e.g. VoteNet). However, point cloud data have inherent limitations. They are sparse, lack color information and often suffer from sensor noise. Images, on the other hand, have high resolution and rich texture. Thus they can complement the 3D geometry provided by point clouds. Yet how to effectively use image information to assist point cloud based detection is still an open question. In this work, we build on top of VoteNet and propose a 3D detection architecture called ImVoteNet specialized for RGB-D scenes. ImVoteNet is based on fusing 2D votes in images and 3D votes in point clouds. Compared to prior work on multi-modal detection, we explicitly extract both geometric and semantic features from the 2D images. We leverage camera parameters to lift these features to 3D. To improve the synergy of 2D-3D feature fusion, we also propose a multi-tower training scheme. We validate our model on the challenging SUN RGB-D dataset, advancing state-of-the-art results by 5.7 mAP. We also provide rich ablation studies to analyze the contribution of each design choice.

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

Deep neural networks are known to be vulnerable to adversarial examples which are carefully crafted instances to cause the models to make wrong predictions. While adversarial examples for 2D images and CNNs have been extensively studied, less attention has been paid to 3D data such as point clouds. Given many safety-critical 3D applications such as autonomous driving, it is important to study how adversarial point clouds could affect current deep 3D models. In this work, we propose several novel algorithms to craft adversarial point clouds against PointNet, a widely used deep neural network for point cloud processing. Our algorithms work in two ways: adversarial point perturbation and adversarial point generation. For point perturbation, we shift existing points negligibly. For point generation, we generate either a set of independent and scattered points or a small number (1-3) of point clusters with meaningful shapes such as balls and airplanes which could be hidden in the human psyche. In addition, we formulate six perturbation measurement metrics tailored to the attacks in point clouds and conduct extensive experiments to evaluate the proposed algorithms on the ModelNet40 3D shape classification dataset. Overall, our attack algorithms achieve a success rate higher than 99% for all targeted attacks.

Research on 2D and 3D generative models typically focuses on the final artifact being created, e.g., an image or a 3D structure. Unlike 2D image generation, the generation of 3D objects in the real world is commonly constrained by the process and order in which the object is constructed. For instance, gravity needs to be taken into account when building a block tower. In this paper, we explore the prediction of ordered actions to construct 3D objects. Instead of predicting actions based on physical constraints, we propose learning through observing human actions. To enable large-scale data collection, we use the Minecraft1 environment. We introduce 3D-Craft, a new dataset of 2,500 Minecraft houses each built by human players sequentially from scratch. To learn from these human action sequences, we propose an order-aware 3D generative model called VoxelCNN. In contrast to other 3D generative models which either have no explicit order (e.g. holistic generation with 3DGAN [35]), or follow a simple heuristic order (e.g. raster-scan), VoxelCNN is trained to imitate human building order with spatial awareness. We also transferred the order to other dataset such as ShapeNet[10]. The 3D-Craft dataset, models, and benchmark system will be made publicly available, which may inspire new directions for future research exploration. https://github.com/facebookresearch/VoxelCNN.

Current 3D object detection methods are heavily influenced by 2D detectors. In order to leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids (i.e., to voxel grids or to bird's eye view images), or rely on detection in 2D images to propose 3D boxes. Few works have attempted to directly detect objects in point clouds. In this work, we return to first principles to construct a 3D detection pipeline for point cloud data and as generic as possible. However, due to the sparse nature of the data - samples from 2D manifolds in 3D space - we face a major challenge when directly predicting bounding box parameters from scene points: a 3D object centroid can be far from any surface point thus hard to regress accurately in one step. To address the challenge, we propose VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting. Our model achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency. Remarkably, VoteNet outperforms previous methods by using purely geometric information without relying on color images.

We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.

In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.

We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution – but complete – output. To this end, we introduce a 3D-Encoder-Predictor Network (3D-EPN) which is composed of 3D convolutional layers. The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space. This allows us to predict global structure in unknown areas at high accuracy. We then correlate these intermediary results with 3D geometry from a shape database at test time. In a final pass, we propose a patch-based 3D shape synthesis method that imposes the 3D geometry from these retrieved shapes as constraints on the coarsely-completed mesh. This synthesis process enables us to reconstruct fine-scale detail and generate high-resolution output while respecting the global mesh structure obtained by the 3D-EPN. Although our 3D-EPN outperforms state-of-the-art completion method, the main contribution in our work lies in the combination of a data-driven shape predictor and analytic 3D shape synthesis. In our results, we show extensive evaluations on a newly-introduced shape completion benchmark for both real-world and synthetic data.

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

Few prior works study deep learning on point sets. PointNet is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-theart methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multiresolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.

Building discriminative representations for 3D data has been an important task in computer graphics and computer vision research. Convolutional Neural Networks (CNNs) have shown to operate on 2D images with great success for a variety of tasks. Lifting convolution operators to 3D (3DCNNs) seems like a plausible and promising next step. Unfortunately, the computational complexity of 3D CNNs grows cubically with respect to voxel resolution. Moreover, since most 3D geometry representations are boundary based, occupied regions do not increase proportionately with the size of the discretization, resulting in wasted computation. In this work, we represent 3D spaces as volumetric fields, and propose a novel design that employs field probing filters to efficiently extract features from them. Each field probing filter is a set of probing points -- sensors that perceive the space. Our learning algorithm optimizes not only the weights associated with the probing points, but also their locations, which deforms the shape of the probing filters and adaptively distributes them in 3D space. The optimized probing points sense the 3D space "intelligently", rather than operating blindly over the entire domain. We show that field probing is significantly more efficient than 3DCNNs, while providing state-of-the-art performance, on classification tasks for 3D object recognition benchmark datasets.

Object viewpoint estimation from 2D images is an essential task in computer vision. However, two issues hinder its progress: scarcity of training data with viewpoint annotations, and a lack of powerful features. Inspired by the growing availability of 3D models, we propose a framework to address both issues by combining render-based image synthesis and CNNs (Convolutional Neural Networks). We believe that 3D models have the potential in generating a large number of images of high variation, which can be well exploited by deep CNN with a high learning capacity. Towards this goal, we propose a scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task. Experimentally, we show that the viewpoint estimation from our pipeline can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark.

Both 3D models and 2D images contain a wealth of information about everyday objects in our environment. However, it is difficult to semantically link together these two media forms, even when they feature identical or very similar objects. We propose a joint embedding space populated by both 3D shapes and 2D images of objects, where the distances between embedded entities reflect similarity between the underlying objects. This joint embedding space facilitates comparison between entities of either form, and allows for cross-modality retrieval. We construct the embedding space using 3D shape similarity measure, as 3D shapes are more pure and complete than their appearance in images, leading to more robust distance metrics. We then employ a Convolutional Neural Network (CNN) to "purify" images by muting distracting factors. The CNN is trained to map an image to a point in the embedding space, so that it is close to a point attributed to a 3D model of a similar object to the one depicted in the image. This purifying capability of the CNN is accomplished with the help of a large amount of training data consisting of images synthesized from 3D shapes. Our joint embedding allows cross-view image retrieval, image-based shape retrieval, as well as shape-based image retrieval. We evaluate our method on these retrieval tasks and show that it consistently out-performs state-of-the-art methods, and demonstrate the usability of a joint embedding in a number of additional applications.