Capturing photo realistic appearance and geometry of scenes is a fundamental problem in computer vision and graphics with a set of mature tools and solutions for content creation [12], [67], large scale scene mapping [5], augmented reality and cinematography [6], [80], [97]. Enthusiast level 3D photogrammetry, especially for small or tabletop scenes, has been supercharged by more capable smartphone cameras and new toolboxes like RealityCapture and NeRF-Studio. A subset of these solutions are geared towards view synthesis where the focus is on photo-realistic view interpolation rather than recovery of accurate scene geometry. These solutions take the “shape-radiance ambiguity”[58] into stride by decoupling the scene transmissivity (related to geometry) from the scene appearance prediction. But without diverse training views, several neural scene representations (e.g. [39], [73], [76]) are prone to poor shape reconstructions while estimating accurate appearance.

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of generating accurate predictions across domains. As a result, state of the art approaches show impressive performance in zero-shot relative and metric depth estimation. Recently, diffusion models have exhibited remarkable scalability and generalizable properties in their learned representations. However, because these models repurpose tools originally designed for image generation, they can only operate on dense ground-truth, which is not available for most depth labels, especially in real-world settings. In this paper we present GRIN, an efficient diffusion model designed to ingest sparse unstructured training data. We use image features with 3D geometric positional encodings to condition the diffusion process both globally and locally, generating depth predictions at a pixel-level. With comprehensive experiments across eight indoor and outdoor datasets, we show that GRIN establishes a new state of the art in zero-shot metric monocular depth estimation even when trained from scratch.

Current methods for 3D scene reconstruction from sparse posed images employ intermediate 3D representations such as neural fields, voxel grids, or 3D Gaussians, to achieve multi-view consistent scene appearance and geometry. In this paper we introduce MVGD, a diffusion-based architecture capable of direct pixel-level generation of images and depth maps from novel viewpoints, given an arbitrary number of input views. Our method uses raymap conditioning to both augment visual features with spatial information from different viewpoints, as well as to guide the generation of images and depth maps from novel views. A key aspect of our approach is the multi-task generation of images and depth maps, using learnable task embeddings to guide the diffusion process towards specific modalities. We train this model on a collection of more than 60 million multi-view samples from publicly available datasets, and propose techniques to enable efficient and consistent learning in such diverse conditions. We also propose a novel strategy that enables the efficient training of larger models by incrementally fine-tuning smaller ones, with promising scaling behavior. Through extensive experiments, we report state-of-the-art results in multiple novel view synthesis benchmarks, as well as multi-view stereo and video depth estimation.

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these issues, we introduce ZeroGrasp, a novel framework that simultaneously performs 3D reconstruction and grasp pose prediction in near real-time. A key insight of our method is that occlusion reasoning and modeling the spatial relationships between objects is beneficial for both accurate reconstruction and grasping. We couple our method with a novel large-scale synthetic dataset, which comprises 1M photo-realistic images, high-resolution 3D reconstructions and 11.3B physically-valid grasp pose annotations for 12K objects from the Objaverse-LVIS dataset. We evaluate Zero-Grasp on the GraspNet-1B benchmark as well as through real-world robot experiments. ZeroGrasp achieves state-of-the-art performance and generalizes to novel real-world objects by leveraging synthetic data. https://sh8.io/#/zerograsp

We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers high-resolution and dense (all-pixel) correspondence fields, which can be visualized as flow maps. Unlike existing optical flow methods, our approach corresponds one frame to hundreds of subsequent frames, rather than just the next frame. We develop a new architecture for this task, blending techniques from existing work in optical flow and point tracking: the model performs iterative inference on low-resolution grids of correspondence estimates, propagating information spatially via 2D convolution layers, and propagating information temporally via pixel-aligned attention layers. The model is fast and parameter-efficient (16 million parameters), and delivers state-of-the-art point tracking accuracy at high resolution (i.e., tracking 768x1024 pixels, on a 40G GPU). A benefit of our design is that we can train jointly on optical flow datasets and point tracking datasets, and we find that doing so is crucial for top performance. We provide an extensive ablation study on our architecture details and training recipe, making it clear which details matter most. Our code and model weights are available at https://alltracker.github.io

Reconstructing articulated objects prevalent in daily environments is crucial for applications in augmented/virtual reality and robotics. However, existing methods face scalability limitations (requiring 3D supervision or costly annotations), robustness issues (being susceptible to local optima), and rendering shortcomings (lacking speed or photorealism). We introduce SplArt, a self-supervised, category-agnostic framework that leverages 3D Gaussian Splatting (3DGS) to reconstruct articulated objects and infer kinematics from two sets of posed RGB images captured at different articulation states, enabling real-time photorealistic rendering for novel viewpoints and articulations. SplArt augments 3DGS with a differentiable mobility parameter per Gaussian, achieving refined part segmentation. A multi-stage optimization strategy is employed to progressively handle reconstruction, part segmentation, and articulation estimation, significantly enhancing robustness and accuracy. SplArt exploits geometric self-supervision, effectively addressing challenging scenarios without requiring 3D annotations or category-specific priors. Evaluations on established and newly proposed benchmarks, along with applications to real-world scenarios using a handheld RGB camera, demonstrate SplArt's state-of-the-art performance and real-world practicality. Code is publicly available at https://github.com/ripl/splart.

We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estimates. To operationalize this insight, we propose an algorithm for estimating question complexity from code. It identifies fine-grained primitives that correlate with the hardest questions for any given set of models, making it easy to scale to new approaches in the future. Finally, to further illustrate the utility of our method, we extend it to automatically generate complex questions, constructing a new benchmark that is 1.9 times harder than the popular NExT-QA.

We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first method of its kind to enable probabilistic pose and shape estimation. OmniShape is based on the key insight that shape completion can be decoupled into two multi-modal distributions: one capturing how measurements project into a normalized object reference frame defined by the dataset and the other modelling a prior over object geometries represented as triplanar neural fields. By training separate conditional diffusion models for these two distributions, we enable sampling multiple hypotheses from the joint pose and shape distri-bution. OmniShape demonstrates compelling performance on challenging real world datasets. Project website: https://tri-ml.glthub.io/omnishape.

This paper studies the problem of concept-based inter-pretability of transformer representations for videos. Con-cretely, we seek to explain the decision-making process of video transformers based on high-level, spatiotemporal concepts that are automatically discovered. Prior research on concept-based interpretability has concentrated solely on image-level tasks. Comparatively, video models deal with the added temporal dimension, increasing complexity and posing challenges in identifying dynamic concepts over time. In this work, we systematically address these challenges by introducing the first Video Transformer Con-cept Discovery (VTCD) algorithm. To this end, we propose an efficient approach for unsupervised identification of units of video transformer representations - concepts, and ranking their importance to the output of a model. The resulting concepts are highly interpretable, revealing spatiotemporal reasoning mechanisms and object-centric representations in unstructured video models. Performing this analysis jointly over a diverse set of supervised and self-supervised representations, we discover that some of these mechanism are universal in video transformers. Finally, we show that VTCD can be usedfor fine-grained action recognition and video object segmentation.

In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data. Our goal is to predict the 3D shape, size, and 6D pose of objects within a single RGB-D image, operating at the category level and eliminating the need for CAD models during inference. While existing self-supervised methods have made strides in this field, they often suffer from inefficiencies arising from non-end-to-end processing, reliance on separate models for different object categories, and slow surface extraction during the training of implicit reconstruction models; thus hindering both the speed and real-world applicability of the 3D recognition process. Our proposed method leverages a multi-stage training pipeline, designed to efficiently transfer synthetic performance to the real-world domain. This approach is achieved through a combination of 2D and 3D supervised losses during the synthetic domain training, followed by the incorporation of 2D supervised and 3D self-supervised losses on real-world data in two additional learning stages. By adopting this comprehensive strategy, our method successfully overcomes the aforementioned limitations and outperforms existing self-supervised 6D pose and size estimation baselines on the NOCS test-set with a 16.4% absolute improvement in mAP for 6D pose estimation while running in near real-time at 5 Hz. Project page: fsd6d.github.io

If robots are to work effectively alongside people, they must be able to interpret natural language references to objects in their 3D environment. Understanding 3D referring expressions is challenging—it requires the ability to both parse the 3D structure of the scene and correctly ground free-form language in the presence of distraction and clutter. We introduce Transcrib3D, an approach that brings together 3D detection methods and the emergent reasoning capabilities of large language models (LLMs). Transcrib3D uses text as the unifying medium, which allows us to sidestep the need to learn shared representations connecting multi-modal inputs, which would require massive amounts of annotated 3D data. As a demonstration of its effectiveness, Transcrib3D achieves state-of-the-art results on 3D reference resolution benchmarks, with a great leap in performance from previous multi-modality baselines. To improve upon zero-shot performance and facilitate local deployment on edge computers and robots, we propose self-correction for fine-tuning that trains smaller models, resulting in performance close to that of large models. We show that our method enables a real robot to perform pick-and-place tasks given queries that contain challenging referring expressions. Code will be available at https://ripl.github.io/Transcrib3D.

This paper addresses the challenging problem of category-level pose estimation. Current state-of-the-art methods for this task face challenges when dealing with symmetric objects and when attempting to generalize to new environments solely through synthetic data training. In this work, we address these challenges by proposing a probabilistic model that relies on diffusion to estimate dense canonical maps crucial for recovering partial object shapes as well as establishing correspondences essential for pose estimation. Furthermore, we introduce critical components to enhance performance by leveraging the strength of the diffusion models with multi-modal input representations. We demonstrate the effectiveness of our method by testing it on a range of real datasets. Despite being trained solely on our generated synthetic data, our approach achieves state-of-the-art performance and unprecedented generalization qualities, outperforming baselines, even those specifically trained on the target domain. Our code and data for the generalization benchmark can be found at https://woven-planet.github.io/DiffusionNOCS/.

Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D learning. Equivariance serves as a valuable inductive prior, aiding in the generation of robust multi-view features for 3D scene understanding. In this paper, we explore the application of equivariant multi-view learning to depth estimation, not only recognizing its significance for computer vision and robotics but also addressing the limitations of previous research. Most prior studies have either overlooked equivariance in this setting or achieved only approximate equivariance through data augmentation, which often leads to inconsistencies across different reference frames. To address this issue, we propose to embed $SE(3)$ equivariance into the Perceiver IO architecture. We employ Spherical Harmonics for positional encoding to ensure 3D rotation equivariance, and develop a specialized equivariant encoder and decoder within the Perceiver IO architecture. To validate our model, we applied it to the task of stereo depth estimation, achieving state of the art results on real-world datasets without explicit geometric constraints or extensive data augmentation.

3D object detection from visual sensors is a corner-stone capability of robotic systems. State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-view camera input. In this work we gain intuition from the integral role of multi-view consistency in 3D scene understanding and geometric learning. To this end, we introduce VEDet, a novel 3D object detection framework that exploits 3D multi-view geometry to improve localization through viewpoint awareness and equivariance. VEDet leverages a query-based transformer architecture and encodes the 3D scene by augmenting image features with positional encodings from their 3D perspective geometry. We design view-conditioned queries at the output level, which enables the generation of multiple virtual frames during training to learn viewpoint equivariance by enforcing multi-view consistency. The multi-view geometry injected at the input level as positional encodings and regularized at the loss level provides rich geometric cues for 3D object detection, leading to state-of-the-art performance on the nuScenes benchmark. The code and model are made available at https://github.com/TRI-ML/VEDet.

We present CARTO, a novel approach for reconstructing multiple articulated objects from a single stereo RGB observation. We use implicit object-centric representations and learn a single geometry and articulation decoder for multiple object categories. Despite training on multiple categories, our decoder achieves a comparable reconstruction accuracy to methods that train bespoke decoders separately for each category. Combined with our stereo image encoder we infer the 3D shape, 6D pose, size, joint type, and the joint state of multiple unknown objects in a single forward pass. Our method achieves a 20.4% absolute improvement in mAP 3D IOU50 for novel instances when compared to a two-stage pipeline. Inference time is fast and can run on a NVIDIA TITAN XP GPU at 1 HZ for eight or less objects present. While only trained on simulated data, CARTO transfers to real-world object instances. Code and evaluation data is available at: carto. cs. uni - freiburg. de

Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with learned scales that cannot be directly transferred across domains. Because of that, recent works focus instead on relative depth, eschewing scale in favor of improved up-to-scale zero-shot transfer. In this work we introduce ZeroDepth, a novel monocular depth estimation framework capable of predicting metric scale for arbitrary test images from different domains and camera parameters. This is achieved by (i) the use of input-level geometric embeddings that enable the network to learn a scale prior over objects; and (ii) decoupling the encoder and decoder stages, via a variational latent representation that is conditioned on single frame information. We evaluated ZeroDepth targeting both outdoor (KITTI, DDAD, nuScenes) and indoor (NYUv2) benchmarks, and achieved a new state-of-the-art in both settings using the same pre-trained model, outperforming methods that train on in-domain data and require test-time scaling to produce metric estimates. Project page: https://sites.google.com/view/tri-zerodepth.

Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate geometries in the case of limited viewpoint diversity, a common scenario in robotics applications. In this work, we propose to use the multi-view photometric objective from the self-supervised depth estimation literature as a geometric regularizer for volumetric rendering, significantly improving novel view synthesis without requiring additional information. Building upon this insight, we explore the explicit modeling of scene geometry using a generalist Transformer, jointly learning a radiance field as well as depth and light fields with a set of shared latent codes. We demonstrate that sharing geometric information across tasks is mutually beneficial, leading to improvements over single-task learning without an increase in network complexity. Our DeLiRa architecture achieves state-of-the-art results on the ScanNet benchmark, enabling high quality volumetric rendering as well as real-time novel view and depth synthesis in the limited viewpoint diversity setting. Our project page is https://sites.google.com/view/tri-delira.

Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views hence limiting their application to real-world unbounded urban settings where the objects of interest or backgrounds are observed from very few views. To mitigate this challenge, we introduce a new approach called NeO 360, Neural fields for sparse view synthesis of outdoor scenes. NeO 360 is a generalizable method that reconstructs 360° scenes from a single or a few posed RGB images. The essence of our approach is in capturing the distribution of complex real-world outdoor 3D scenes and using a hybrid image-conditional triplanar representation that can be queried from any world point. Our representation combines the best of both voxel-based and bird’s-eye-view (BEV) representations and is more effective and expressive than each. NeO 360’s representation allows us to learn from a large collection of unbounded 3D scenes while offering generalizability to new views and novel scenes from as few as a single image during inference. We demonstrate our approach on the pro posed challenging 360° unbounded dataset, called NeRDS 360, and show that NeO 360 outperforms state-of-the-art generalizable methods for novel view synthesis while also offering editing and composition capabilities. Project page: zubair-irshad.github.io/projects/neo360.html

Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors. Recent research has developed a variety of camera-only methods, where features are differentiably “lifted” from the multi-camera images onto the 2D ground plane, yielding a “bird's eye view” (BEV) feature representation of the 3D space around the vehicle. This line of work has produced a variety of novel “lifting” methods, but we observe that other details in the training setups have shifted at the same time, making it unclear what really matters in top-performing methods. We also observe that using cameras alone is not a real-world constraint, considering that additional sensors like radar have been integrated into real vehicles for years already. In this paper, we first of all attempt to elucidate the high-impact factors in the design and training protocol of BEV perception models. We find that batch size and input resolution greatly affect performance, while lifting strategies have a more modest effect-even a simple parameter-free lifter works well. Second, we demonstrate that radar data can provide a substantial boost to performance, helping to close the gap between camera-only and LiDAR-enabled systems. We analyze the radar usage details that lead to good performance, and invite the community to re-consider this commonly-neglected part of the sensor platform.

Autonomous vehicles and robots need to operate over a wide variety of scenarios in order to complete tasks efficiently and safely. Multi-camera self-supervised monocular depth estimation from videos is a promising way to reason about the environment, as it generates metrically scaled geometric predictions from visual data without requiring additional sensors. However, most works assume well-calibrated extrinsics to fully leverage this multi-camera setup, even though accurate and efficient calibration is still a challenging problem. In this work, we introduce a novel method for extrinsic calibration that builds upon the principles of self-supervised monocular depth and ego-motion learning. Our proposed curriculum learning strategy uses monocular depth and pose estimators with velocity supervision to estimate extrinsics, and then jointly learns extrinsic calibration along with depth and pose for a set of overlapping cameras rigidly attached to a moving vehicle. Experiments on a benchmark multi-camera dataset (DDAD) demonstrate that our method enables self-calibration in various scenes robustly and efficiently compared to a traditional vision-based pose estimation pipeline. Furthermore, we demonstrate the benefits of extrinsics self-calibration as a way to improve depth prediction via joint optimization. The project page: https://sites.google.com/tri.global/tri-sesc

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching for self-supervised monocular depth estimation, and propose a novel transformer architecture for cost volume generation. We use depth-discretized epipolar sampling to select matching candidates, and refine predictions through a series of self- and cross-attention layers. These layers sharpen the matching probability between pixel features, improving over standard similarity metrics prone to ambiguities and local minima. The refined cost volume is decoded into depth estimates, and the whole pipeline is trained end-to-end from videos using only a photometric objective. Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures. We also show that our learned cross-attention network yields representations transferable across datasets, increasing the effectiveness of pre-training strategies. Project page: https://sites.google.com/tri.global/depthformer.

Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence for mobile robots and autonomous vehicles. In contrast, self-supervised depth and ego-motion estimation approaches can bypass explicit calibration by in-ferring per-frame projection models that optimize a view-synthesis objective. In this paper, we extend this approach to explicitly calibrate a wide range of cameras from raw videos in the wild. We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods. We validate our approach on a wide variety of camera geometries, including perspective, fisheye, and catadioptric. Finally, we show that our approach leads to improvements in the downstream task of depth estimation, achieving state-of-the-art results on the EuRoC dataset with greater computational efficiency than contemporary methods. The project page: https://sites.google.com/ttic.edu/self-sup-self-calib

Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image (monodepth) with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Auxiliary Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion, depending on whether only RGB images or also sparse point clouds are available at inference time. First, we decouple the image and depth map encoding stages using sparse convolutions to process only the valid depth map pixels. Second, we inject this information, when available, into the skip connections of the depth prediction network, augmenting its features. Through extensive experimental analysis on one indoor (NYUv2) and two outdoor (KITTI and DDAD) benchmarks, we demonstrate that our proposed SAN architecture is able to simultaneously learn both tasks, while achieving a new state of the art in depth prediction by a significant margin.

Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatically annotating video sequences by propagating sparsely labeled frames through time is a more scalable alternative. In this work, we propose a novel label propagation method, termed Warp-Refine Propagation, that combines semantic cues with geometric cues to efficiently auto-label videos. Our method learns to refine geometrically-warped labels and infuse them with learned semantic priors in a semi-supervised setting by leveraging cycle-consistency across time. We quantitatively show that our method improves label-propagation by a noteworthy margin of 13.1 mIoU on the ApolloScape dataset. Furthermore, by training with the auto-labelled frames, we achieve competitive results on three semantic-segmentation benchmarks, improving the state-of-the-art by a large margin of 1.8 and 3.61 mIoU on NYU-V2 and KITTI, while matching the current best results on Cityscapes.

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA)1learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on videos. GUDA establishes a new state of the art in UDA for semantic segmentation on three benchmarks, outperforming methods that use domain adversarial learning, self-training, or other self-supervised proxy tasks. Furthermore, we show that our method scales well with the quality and quantity of synthetic data while also improving depth prediction.

Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These two-stage detectors improve with the accuracy of the intermediate depth estimation network, which can itself be improved without manual labels via large-scale self-supervised learning. However, they tend to suffer from overfitting more than end-to-end methods, are more complex, and the gap with similar lidar-based detectors remains significant. In this work, we propose an end-to-end, single stage, monocular 3D object detector, DD3D, that can benefit from depth pre-training like pseudo-lidar methods, but without their limitations. Our architecture is designed for effective information transfer between depth estimation and 3D detection, allowing us to scale with the amount of unlabeled pre-training data. Our method achieves state-of-the-art results on two challenging benchmarks, with 16.34% and 9.28% AP for Cars and Pedestrians (respectively) on the KITTI-3D benchmark, and 41.5% mAP on NuScenes.

Multi-object tracking is an important ability for an autonomous vehicle to safely navigate a traffic scene. Current state-of-the-art follows the tracking-by-detection paradigm where existing tracks are associated with detected objects through some distance metric. Key challenges to increase tracking accuracy lie in data association and track life cycle management. We propose a probabilistic, multi-modal, multiobject tracking system consisting of different trainable modules to provide robust and data-driven tracking results. First, we learn how to fuse features from 2D images and 3D LiDAR point clouds to capture the appearance and geometric information of an object. Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association. And third, we propose to learn when to initialize a track from an unmatched object detection. Through extensive quantitative and qualitative results, we show that when using the same object detectors our method outperforms state-of-the-art approaches on the NuScenes and KITTI datasets.

Self-supervised learning has emerged as a powerful tool for depth and ego-motion estimation, leading to state-of-the-art results on benchmark datasets. However, one significant limitation shared by current methods is the assumption of a known parametric camera model - usually the standard pinhole geometry - leading to failure when applied to imaging systems that deviate significantly from this assumption (e.g., catadioptric cameras or underwater imaging). In this work, we show that self-supervision can be used to learn accurate depth and ego-motion estimation without prior knowledge of the camera model. Inspired by the geometric model of Grossberg and Nayar, we introduce Neural Ray Surfaces (NRS), convolutional networks that represent pixel-wise projection rays, approximating a wide range of cameras. NRS are fully differentiable and can be learned end-to-end from unlabeled raw videos. We demonstrate the use of NRS for self-supervised learning of visual odometry and depth estimation from raw videos obtained using a wide variety of camera systems, including pinhole, fisheye, and catadioptric.

Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.

Safe autonomous driving requires robust detection of other traffic participants. However, robust does not mean perfect, and safe systems typically minimize missed detections at the expense of a higher false positive rate. This results in conservative and yet potentially dangerous behavior such as avoiding imaginary obstacles. In the context of behavioral cloning, perceptual errors at training time can lead to learning difficulties or wrong policies, as expert demonstrations might be inconsistent with the perceived world state. In this work, we propose a behavioral cloning approach that can safely leverage imperfect perception without being conservative. Our core contribution is a novel representation of perceptual uncertainty for learning to plan. We propose a new probabilistic birds-eye-view semantic grid to encode the noisy output of object perception systems. We then leverage expert demonstrations to learn an imitative driving policy using this probabilistic representation. Using the CARLA simulator, we show that our approach can safely overcome critical false positives that would otherwise lead to catastrophic failures or conservative behavior.

Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular depth prediction. Inspired by recent deep learning methods for Single-Image Super-Resolution, we propose a subpixel convolutional layer extension for depth super-resolution that accurately synthesizes high-resolution disparities from their corresponding low-resolution convolutional features. In addition, we introduce a differentiable flip-augmentation layer that accurately fuses predictions from the image and its horizontally flipped version, reducing the effect of left and right shadow regions generated in the disparity map due to occlusions. Both contributions provide significant performance gains over the state-of-the-art in self-supervised depth and pose estimation on the public KITTI benchmark. A video of our approach can be found at https://youtu.be/jKNgBeBMx0I.

We present an approach to automatically assign semantic labels to rooms reconstructed from 3D RGB maps of apartments. Evidence for the room types is generated using state-of-the-art deep-learning techniques for scene classification and object detection based on automatically generated virtual RGB views, as well as from a geometric analysis of the map's 3D structure. The evidence is merged in a conditional random field, using statistics mined from different datasets of indoor environments. We evaluate our approach qualitatively and quantitatively and compare it to related methods.

We present a system for creating object models from RGB-D views acquired autonomously by a mobile robot. We create high-quality textured meshes of the objects by approximating the underlying geometry with a Poisson surface. Our system employs two optimization steps, first registering the views spatially based on image features, and second aligning the RGB images to maximize photometric consistency with respect to the reconstructed mesh. We show that the resulting models can be used robustly for recognition by training a Convolutional Neural Network (CNN) on images rendered from the reconstructed meshes. We perform experiments on data collected autonomously by a mobile robot both in controlled and uncontrolled scenarios. We compare quantitatively and qualitatively to previous work to validate our approach.

We present a novel approach to mobile robot search for non-stationary objects in partially known environments. We formulate the search as a path planning problem in an environment where the probability of object occurrences at particular locations is a function of time. We propose to explicitly model the dynamics of the object occurrences by their frequency spectra. Using this spectral model, our path planning algorithm can construct plans that reflect the likelihoods of object locations at the time the search is performed. Three datasets collected over several months containing person and object occurrences in residential and office environments were chosen to evaluate the approach. Several types of spatio-temporal models were created for each of these datasets and the efficiency of the search method was assessed by measuring the time it took to locate a particular object. The results indicate that modeling the dynamics of object occurrences reduces the search time by 25% to 65% compared to maps that neglect these dynamics.

We present a novel method for clustering segmented dynamic parts of indoor RGB-D scenes across repeated observations by performing an analysis of their spatial-temporal distributions. We segment areas of interest in the scene using scene differencing for change detection. We extend the Meta-Room method and evaluate the performance on a complex dataset acquired autonomously by a mobile robot over a period of 30 days. We use an initial clustering method to group the segmented parts based on appearance and shape, and we further combine the clusters we obtain by analyzing their spatial-temporal behaviors. We show that using the spatial-temporal information further increases the matching accuracy.

Long-term autonomous learning of human environments entails modelling and generalizing over distinct variations in: object instances in different scenes, and different scenes with respect to space and time. It is crucial for the robot to recognize the structure and context in spatial arrangements and exploit these to learn models which capture the essence of these distinct variations. Table-tops posses a typical structure repeatedly seen in human environments and are identified by characteristics of being personal spaces of diverse functionalities and dynamically changing due to human interactions. In this paper, we present a 3D dataset of 20 office table-tops manually observed and scanned 3 times a day as regularly as possible over 19 days (461 scenes) and subsequently, manually annotated with 18 different object classes, including multiple instances. We analyse the dataset to discover spatial structures and patterns in their variations. The dataset can, for example, be used to study the spatial relations between objects and long-term environment models for applications such as activity recognition, context and functionality estimation and anomaly detection.

We present a novel method for re-creating the static structure of cluttered office environments - which we define as the “meta-room” - from multiple observations collected by an autonomous robot equipped with an RGB-D depth camera over extended periods of time. Our method works directly with point clusters by identifying what has changed from one observation to the next, removing the dynamic elements and at the same time adding previously occluded objects to reconstruct the underlying static structure as accurately as possible. The process of constructing the meta-rooms is iterative and it is designed to incorporate new data as it becomes available, as well as to be robust to environment changes. The latest estimate of the meta-room is used to differentiate and extract clusters of dynamic objects from observations. In addition, we present a method for re-identifying the extracted dynamic objects across observations thus mapping their spatial behaviour over extended periods of time.

This paper presents a novel approach to model motion patterns of dynamic objects, such as people and vehicles, in the environment with the occupancy grid map representation. Corresponding to the ever-changing nature of the motion pattern of dynamic objects, we model each occupancy grid cell by an IOHMM, which is an inhomogeneous variant of the HMM. This distinguishes our work from existing methods which use the conventional HMM, assuming motion evolving according to a stationary process. By introducing observations of neighbor cells in the previous time step as input of IOHMM, the transition probabilities in our model are dependent on the occurrence of events in the cell's neighborhood. This enables our method to model the spatial correlation of dynamics across cells. A sequence processing example is used to illustrate the advantage of our model over conventional HMM based methods. Results from the experiments in an office corridor environment demonstrate that our method is capable of capturing dynamics of such human living environments.

Exploration of unknown environments remains one of the fundamental problems of mobile robotics. It is also a prime example for a task that can benefit significantly from multi-robot teams. We present an integrated system for semi-autonomous cooperative exploration, augmented by an intuitive user interface for efficient human supervision and control. In this preliminary study we demonstrate the effectiveness of the system as a whole and the intuitive interface in particular. Congruent with previous findings, results confirm that having a human in the loop improves task performance, especially with larger numbers of robots. Specific to our interface, we find that even untrained operators can efficiently manage a decently sized team of robots.