Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision. However, most existing approaches do not generalize well across different domains and scene types (e.g. indoor vs. outdoor). Training a general-purpose multi-view stereo model is challenging and raises several questions, e.g. how to best make use of transformer-based architectures, how to incorporate additional metadata when there is a variable number of input views, and how to estimate the range of valid depths which can vary considerably across different scenes and is typically not known a priori? To address these issues, we introduce MVSA, a novel and versatile Multi-View Stereo architecture that aims to work Anywhere by generalizing across diverse domains and depth ranges. MVSA combines monocular and multi-view cues with an adaptive cost volume to deal with scale-related issues. We demonstrate state-of-the-art zero-shot depth estimation on the Robust Multi-View Depth Benchmark, surpassing existing multi-view stereo and monocular baselines.

Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene from posed images. Our first finding is that a surprisingly competitive baseline results from combining popular clustering algorithms with recent improvements in 3D geometry estimation. However, such purely geometric methods are understandably oblivious to plane semantics, which are crucial to discerning distinct planes. To overcome this limitation, we propose a method that predicts multi-view consistent plane embeddings that complement geometry when clustering points into planes. We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches and our strong geometric baseline for the task of plane estimation.

For augmented reality (AR), it is important that virtual assets appear to ‘sit among’ real world objects. The virtual element should variously occlude and be occluded by real matter, based on a plausible depth ordering. This occlusion should be consistent over time as the viewer's camera moves. Unfortunately, small mistakes in the estimated scene depth can ruin the downstream occlusion mask, and thereby the AR illusion. Especially in real-time settings, depths inferred near boundaries or across time can be inconsistent. In this paper, we challenge the need for depth-regression as an intermediate step. We instead propose an implicit model for depth and use that to predict the occlusion mask directly. The inputs to our network are one or more color images, plus the known depths of any virtual geometry. We show how our occlusion predictions are more accurate and more temporally stable than predictions derived from traditional depth-estimation models. We obtain state-of-the-art occlusion results on the challenging ScanNetv2 dataset and superior qualitative results on real scenes.

Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Before sharing a NeRF, though, it might be desirable to remove personal information or unsightly objects. Such removal is not easily achieved with the current NeRF editing frameworks. We propose a framework to remove objects from a NeRF representation created from an RGBD sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a userprovided mask. Our algorithm is underpinned by a confidence based view selection procedure. It chooses which of the individual 2D inpainted images to use in the creation of the NeRF, so that the resulting inpainted NeRF is 3D consistent. We show that our method for NeRF editing is effective for synthesizing plausible inpaintings in a multi-view coherent manner, outperforming competing methods. We validate our approach by proposing a new and still-challenging dataset for the task of NeRF inpainting.

3D scene reconstruction from a sequence of posed RGB images is a cornerstone task for computer vision and augmented reality (AR). While depth-based fusion is the foundation of most real-time approaches for 3D reconstruction, recent learning based methods that operate directly on RGB images can achieve higher quality reconstructions, but at the cost of increased runtime and memory requirements, making them unsuitable for AR applications. We propose an efficient learning-based method that refines the 3D reconstruction obtained by a traditional fusion approach. By leveraging a top-down heightfield representation, our method remains real-time while approaching the quality of other learning-based methods. Despite being a simplification, our heightfield is perfectly appropriate for robotic path planning or augmented reality character placement. We outline several innovations that push the performance beyond existing top-down prediction baselines, and we present an evaluation framework on the challenging ScanNetV2 dataset, targeting AR tasks.

Our goal is to forecast the near future given a set of recent observations. We think this ability to forecast, i.e., to anticipate, is integral for the success of autonomous agents which need not only passively analyze an observation but also must react to it in real-time. Importantly, accurate forecasting hinges upon the chosen scene decomposition. We think that superior forecasting can be achieved by decomposing a dynamic scene into individual ‘things’ and background ‘stuff’. Background ‘stuff’ largely moves because of camera motion, while foreground ‘things’ move because of both camera and individual object motion. Following this decomposition, we introduce panoptic segmentation forecasting. Panoptic segmentation forecasting opens up a middle-ground between existing extremes, which either forecast instance trajectories or predict the appearance of future image frames. To address this task we develop a two-component model: one component learns the dynamics of the background stuff by anticipating odometry, the other one anticipates the dynamics of detected things. We establish a leaderboard for this novel task, and validate a state-of-the-art model that outperforms available baselines.

We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which is integrated in a fully differentiable encoder-decoder architecture. We demonstrate that we can reconstruct high-fidelity depth maps by predicting sparse wavelet coefficients.In contrast with previous works, we show that wavelet coefficients can be learned without direct supervision on coefficients. Instead we supervise only the final depth image that is reconstructed through the inverse wavelet transform. We additionally show that wavelet coefficients can be learned in fully self-supervised scenarios, without access to ground-truth depth. Finally, we apply our method to different state-of-the-art monocular depth estimation models, in each case giving similar or better results compared to the original model, while requiring less than half the multiply-adds in the decoder network.

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also available at test time. The vast majority of monocular networks do not make use of this extra signal, thus ignoring valuable information that could be used to improve the predicted depth. Those that do, either use computationally expensive test-time refinement techniques or off-the- shelf recurrent networks, which only indirectly make use of the geometric information that is inherently available.We propose ManyDepth, an adaptive approach to dense depth estimation that can make use of sequence information at test time, when it is available. Taking inspiration from multi-view stereo, we propose a deep end-to-end cost volume based approach that is trained using self-supervision only. We present a novel consistency loss that encourages the network to ignore the cost volume when it is deemed unreliable, e.g. in the case of moving objects, and an augmentation scheme to cope with static cameras. Our detailed experiments on both KITTI and Cityscapes show that we outperform all published self-supervised baselines, including those that use single or multiple frames at test time.

Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to the camera, which is of limited use when planning paths for robots or augmented reality agents. Such agents can only move when grounded on a traversable surface, which we define as the set of classes which humans can also walk over, such as grass, footpaths and pavement. Models which predict beyond the line of sight often parameterize the scene with voxels or meshes, which can be expensive to use in machine learning frameworks. We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input. We learn from stereo video sequences, using camera poses, per-frame depth and semantic segmentation to form training data, which is used to supervise an image-to-image network. We train models from the KITTI driving dataset, the indoor Matterport dataset, and from our own casually captured stereo footage. We find that a surprisingly low bar for spatial coverage of training scenes is required. We validate our algorithm against a range of strong baselines, and include an assessment of our predictions for a path-planning task.

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser-scans or other ground-truth data. The disadvantage, however, is that the photometric reprojection losses used with self-supervised learning typically have multiple local minima. These plausible-looking alternatives to ground-truth can restrict what a regression network learns, causing it to predict depth maps of limited quality. As one prominent example, depth discontinuities around thin structures are often incorrectly estimated by current state-of-the-art methods. Here, we study the problem of ambiguous reprojections in depth-prediction from stereo-based self-supervision, and introduce Depth Hints to alleviate their effects. Depth Hints are complementary depth-suggestions obtained from simple off-the-shelf stereo algorithms. These hints enhance an existing photometric loss function, and are used to guide a network to learn better weights. They require no additional data, and are assumed to be right only sometimes. We show that using our Depth Hints gives a substantial boost when training several leading self-supervised-from-stereo models, not just our own. Further, combined with other good practices, we produce state-of-the-art depth predictions on the KITTI benchmark.

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple possible pixel values that could plausibly complete occluded image regions. State-of-the art supervised learning methods are typically optimized to make a single test-time prediction for each query, failing to find other modes in the output space. Existing methods that allow for sampling often sacrifice speed or accuracy. We introduce a simple method for training a neural network, which enables diverse structured predictions to be made for each test-time query. For a single input, we learn to predict a range of possible answers. We compare favorably to methods that seek diversity through an ensemble of networks. Such stochastic multiple choice learning faces mode collapse, where one or more ensemble members fail to receive any training signal. Our best performing solution can be deployed for various tasks, and just involves small modifications to the existing single-mode architecture, loss function, and training regime. We demonstrate that our method results in quantitative improvements across three challenging tasks: 2D image completion, 3D volume estimation, and flow prediction.

Passive acoustic sensing has emerged as a powerful tool for quantifying anthropogenic impacts on biodiversity, especially for echolocating bat species. To better assess bat population trends there is a critical need for accurate, reliable, and open source tools that allow the detection and classification of bat calls in large collections of audio recordings. The majority of existing tools are commercial or have focused on the species classification task, neglecting the important problem of first localizing echolocation calls in audio which is particularly problematic in noisy recordings. We developed a convolutional neural network based open-source pipeline for detecting ultrasonic, full-spectrum, search-phase calls produced by echolocating bats. Our deep learning algorithms were trained on full-spectrum ultrasonic audio collected along road-transects across Europe and labelled by citizen scientists from www.batdetective.org. When compared to other existing algorithms and commercial systems, we show significantly higher detection performance of search-phase echolocation calls with our test sets. As an example application, we ran our detection pipeline on bat monitoring data collected over five years from Jersey (UK), and compared results to a widely-used commercial system. Our detection pipeline can be used for the automatic detection and monitoring of bat populations, and further facilitates their use as indicator species on a large scale. Our proposed pipeline makes only a small number of bat specific design decisions, and with appropriate training data it could be applied to detecting other species in audio. A crucial novelty of our work is showing that with careful, non-trivial, design and implementation considerations, state-of-the-art deep learning methods can be used for accurate and efficient monitoring in audio.

Building a complete 3D model of a scene, given only a single depth image, is underconstrained. To gain a full volumetric model, one needs either multiple views, or a single view together with a library of unambiguous 3D models that will fit the shape of each individual object in the scene. We hypothesize that objects of dissimilar semantic classes often share similar 3D shape components, enabling a limited dataset to model the shape of a wide range of objects, and hence estimate their hidden geometry. Exploring this hypothesis, we propose an algorithm that can complete the unobserved geometry of tabletop-sized objects, based on a supervised model trained on already available volumetric elements. Our model maps from a local observation in a single depth image to an estimate of the surface shape in the surrounding neighborhood. We validate our approach both qualitatively and quantitatively on a range of indoor object collections and challenging real scenes.

We introduce a method to discover objects from RGB-D image collections which does not require a user to specify the number of objects expected to be found. We propose a probabilistic formulation to find pairwise similarity between image segments, using a classifier trained on labelled pairs from the recently released RGB-D Object Dataset. We then use a correlation clustering solver to both find the optimal clustering of all the segments in the collection and to recover the number of clusters. Unlike traditional supervised learning methods, our training data need not be of the same class or category as the objects we expect to discover. We show that this parameter-free supervised clustering method has superior performance to traditional clustering methods.

Recent work in the domain of classification of point clouds has shown that topic models can be suitable tools for inferring class groupings in an unsupervised manner. However, point clouds are frequently subject to non-negligible amounts of sensor noise. In this paper, we analyze the effect on classification accuracy of noise added to both an artificial data set and data collected from a Light Detection and Ranging (LiDAR) scanner, and show that topic models are less robust to ‘misspelled’ words than the more näive k-means classifier. Furthermore, standard spin images prove to be a more robust feature under noise than their derivative, ‘angular’ spin images. We additionally show that only a small subset of local features are required in order to give comparable classification accuracy to a full feature set.