Virtual Occlusions Through Implicit Depth

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.

Removing Objects From Neural Radiance Fields

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 RGB-D sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a user-provided 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. We validate our approach using a new and still-challenging dataset for the task of NeRF inpainting.

SimpleRecon: 3D Reconstruction Without 3D Convolutions

Traditionally, 3D indoor scene reconstruction from posed images happens in two phases: per-image depth estimation, followed by depth merging and surface reconstruction. Recently, a family of methods have emerged that perform reconstruction directly in final 3D volumetric feature space. While these methods have shown impressive reconstruction results, they rely on expensive 3D convolutional layers, limiting their application in resource-constrained environments. In this work, we instead go back to the traditional route, and show how focusing on high quality multi-view depth prediction leads to highly accurate 3D reconstructions using simple off-the-shelf depth fusion. We propose a simple state-of-the-art multi-view depth estimator with two main contributions: 1) a carefully-designed 2D CNN which utilizes strong image priors alongside a plane-sweep feature volume and geometric losses, combined with 2) the integration of keyframe and geometric metadata into the cost volume which allows informed depth plane scoring. Our method achieves a significant lead over the current state-of-the-art for depth estimation and close or better for 3D reconstruction on ScanNet and 7-Scenes, yet still allows for online real-time low-memory reconstruction. Code, models and results are available at https://nianticlabs.github.io/simplerecon

Single Image Depth Estimation using Wavelet Decomposition

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. Code at https://github.com/nianticlabs/wavelet-monodepth

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

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.

Panoptic Segmentation Forecasting

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.

DiverseNet: When One Right Answer is not Enough

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.

Learning Stereo from Single Images

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of accurate dense correspondence data is very challenging. We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs. Inspired by recent progress in monocular depth estimation, we generate plausible disparity maps from single images. In turn, we use those flawed disparity maps in a carefully designed pipeline to generate stereo training pairs. Training in this manner makes it possible to convert any collection of single RGB images into stereo training data. This results in a significant reduction in human effort, with no need to collect real depths or to hand-design synthetic data. We can consequently train a stereo matching network from scratch on datasets like COCO, which were previously hard to exploit for stereo. Through extensive experiments we show that our approach outperforms stereo networks trained with standard synthetic datasets, when evaluated on KITTI, ETH3D, and Middlebury.

Footprints and Free Space from a Single Color Image

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.