This paper investigates the generation of realistic full-body human motion using a single head-mounted device with an outward-facing color camera and the ability to perform visual SLAM. To address the ambiguity of this setup, we present HMD2, a novel system that balances motion reconstruction and generation. From a reconstruction stand-point, it aims to maximally utilize the camera streams to produce both analytical and learned features, including head motion, SLAM point cloud, and image embeddings. On the generative front, HMD2 employs a multi-modal conditional motion diffusion model with a Transformer back-bone to maintain temporal coherence of generated motions, and utilizes autoregressive inpainting to facilitate online motion inference with minimal latency (0.17 seconds). We show that our system provides an effective and robust so-lution that scales to a diverse dataset of over 200 hours of motion in complex indoor and outdoor environments.

In this paper, we question whether we have a reliable self-supervised point cloud model that can be used for diverse 3D tasks via simple linear probing, even with limited data and minimal computation. We find that existing 3D self-supervised learning approaches fall short when evaluated on representation quality through linear probing. We hypothesize that this is due to what we term the "geometric shortcut", which causes representations to collapse to low-level spatial features. This challenge is unique to 3D and arises from the sparse nature of point cloud data. We address it through two key strategies: obscuring spatial information and enhancing the reliance on input features, ultimately composing a Sonata of 140k point clouds through self-distillation. Sonata is simple and intuitive, yet its learned representations are strong and reliable: zero-shot visualizations demonstrate semantic grouping, alongside strong spatial reasoning through nearest-neighbor relationships. Sonata demonstrates exceptional parameter and data efficiency, tripling linear probing accuracy (from 21.8% to 72.5%) on ScanNet and nearly doubling performance with only 1% of the data compared to previous approaches. Full fine-tuning further advances SOTA across both 3D indoor and outdoor perception tasks.

We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pickup, observe, and put-down actions, the subjects perform actions typical for a kitchen, office, and living room environment. The recordings include multiple synchronized data streams containing egocentric multi-view RGB/monochrome images, eye gaze signal, scene point clouds, and 3D poses of cameras, hands, and objects. The dataset is recorded with two headsets from Meta: Project Aria, which is a research prototype of AI glasses, and Quest 3, a virtual-reality headset that has shipped millions of units. Ground-truth poses were obtained by a motion-capture system using small optical markers attached to hands and objects. Hand annotations are provided in the UmeTrack and MANO formats, and objects are represented by 3D meshes with PBR materials obtained by an in-house scanner. In our experiments, we demonstrate the effectiveness of multi-view egocentric data for three popular tasks: 3D hand tracking, model-based 6DoF object pose estimation, and 3D lifting of unknown in-hand objects. The evaluated multi-view methods, whose benchmarking is uniquely enabled by HOT3D, significantly outperform their single-view counterparts.

We introduce Digital Twin Catalog (DTC), a new large-scale photorealistic 3D object digital twin dataset. A digital twin of a 3D object is a highly detailed, virtually indistinguishable representation of a physical object, accurately capturing its shape, appearance, physical properties, and other attributes. Recent advances in neural-based 3D reconstruction and inverse rendering have significantly improved the quality of 3D object reconstruction. Despite these advancements, there remains a lack of a large-scale, digital twin quality real-world dataset and benchmark that can quantitatively assess and compare the performance of different reconstruction methods, as well as improve reconstruction quality through training or fine-tuning. Moreover, to democratize 3D digital twin creation, it is essential to integrate creation techniques with next-generation egocentric computing platforms, such as AR glasses. Currently, there is no dataset available to evaluate 3D object reconstruction using egocentric captured images. To address these gaps, the DTC dataset features 2,000 scanned digital twin-quality 3D objects, along with image sequences captured under different lighting conditions using DSLR cameras and egocentric AR glasses. This dataset establishes the first comprehensive real-world evaluation benchmark for 3D digital twin creation tasks, offering a robust foundation for comparing and improving existing reconstruction methods. The DTC dataset is already released at https://www.projectaria.com/datasets/dtc/ and we will also make the baseline evaluations open-source.

As wearable devices become more prevalent, understanding the user’s motion is crucial for improving contextual AI systems. We introduce EgoLM, a versatile framework designed for egocentric motion understanding using multi-modal data. EgoLM integrates the rich contextual information from egocentric videos and motion sensors afforded by wearable devices. It also combines dense supervision signals from motion and language, leveraging the vast knowledge encoded in pre-trained large language models (LLMs). EgoLM models the joint distribution of egocentric motions and natural language using LLMs, conditioned on observations from egocentric videos and motion sensors. It unifies a range of motion understanding tasks, including motion narration from video or motion data, as well as motion generation from text or sparse sensor data. Unique to wearable devices, it also enables a novel task to generate text descriptions from sparse sensors. Through extensive experiments, we validate the effectiveness of EgoLM in addressing the challenges of under-constrained egocentric motion learning, and demonstrate its capability as a generalist model through a variety of applications. Project page: https://hongfz16.github.io/projects/EgoLM.

We present Large Inverse Rendering Model (LIRM), a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second. Our model builds upon the recent Large Reconstruction Models (LRMs) that achieve state-of-the-art sparse-view reconstruction quality. However, existing LRMs struggle to reconstruct unseen parts accurately and cannot recover glossy appearance or generate relightable 3D contents that can be consumed by standard Graphics engines. To address these limitations, we make three key technical contributions to build a more practical multi-view 3D reconstruction framework. First, we introduce an update model that allows us to progressively add more input views to improve our reconstruction. Second, we propose a hexa-plane neural SDF representation to better recover detailed textures, geometry and material parameters. Third, we develop a novel neural directional-embedding mechanism to handle view-dependent effects. Trained on a large-scale shape and material dataset with a tailored coarse-to-fine training scheme, our model achieves compelling results. It compares favorably to optimization-based dense-view inverse rendering methods in terms of geometry and relighting accuracy, while requiring only a fraction of the inference time.

This paper presents Segment This Thing (STT), a new efficient image segmentation model designed to produce a single segment given a single point prompt. Instead of following prior work and increasing efficiency by decreasing model size, we gain efficiency by foveating input images. Given an image and a point prompt, we extract a crop centered on the prompt and apply a novel variable-resolution patch tokenization in which patches are downsampled at a rate that increases with increased distance from the prompt. This approach yields far fewer image tokens than uniform patch tokenization. As a result we can drastically reduce the computational cost of segmentation without reducing model size. Furthermore, the foveation focuses the model on the region of interest, a potentially useful inductive bias. We show that our Segment This Thing model is more efficient than prior work while remaining competitive on segmentation benchmarks. It can easily run at interactive frame rates on consumer hardware and is thus a promising tool for augmented reality or robotics applications.

We present a novel human-in-the-loop approach to estimate 3D scene layout that uses human feedback from an egocentric standpoint. We study this approach through introduction of a novel local correction task, where users identify local errors and prompt a model to automatically correct them. Building on SceneScript, a state-of-the-art framework for 3D scene layout estimation that leverages structured language, we propose a solution that structures this problem as "infilling", a task studied in natural language processing. We train a multi-task version of SceneScript that maintains performance on global predictions while significantly improving its local correction ability. We integrate this into a human-in-the-loop system, enabling a user to iteratively refine scene layout estimates via a low-friction "one-click fix'' workflow. Our system enables the final refined layout to diverge from the training distribution, allowing for more accurate modelling of complex layouts.

We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM), the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene. Feed-forward scene reconstruction has gained significant attention for its ability to rapidly create digital replicas of real-world environments. However, most existing models are limited to static scenes and fail to reconstruct the motion of moving objects. Developing a feed-forward model for dynamic scene reconstruction poses significant challenges, including the scarcity of training data and the need for appropriate 3D representations and training paradigms. To address these challenges, we introduce several key technical contributions: an enhanced large-scale synthetic dataset with ground-truth multi-view videos and dense 3D scene flow supervision; a per-pixel deformable 3D Gaussian representation that is easy to learn, supports high-quality dynamic view synthesis, and enables long-range 3D tracking; and a large transformer network that achieves real-time, generalizable dynamic scene reconstruction. Extensive qualitative and quantitative experiments demonstrate that DGS-LRM achieves dynamic scene reconstruction quality comparable to optimization-based methods, while significantly outperforming the state-of-the-art predictive dynamic reconstruction method on real-world examples. Its predicted physically grounded 3D deformation is accurate and can be readily adapted for long-range 3D tracking tasks, achieving performance on par with state-of-the-art monocular video 3D tracking methods.

We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We proposed a novel density control strategy in training, which enables our 4DGT to handle longer space-time input. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can outperform prior Gaussian-based networks significantly in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.

To enable egocentric contextual AI in always-on smart glasses, it is crucial to be able to keep a record of the user's interactions with the world, including during reading. In this paper, we introduce a new task of reading recognition to determine when the user is reading. We first introduce the first-of-its-kind large-scale multimodal Reading in the Wild dataset, containing 100 hours of reading and non-reading videos in diverse and realistic scenarios. We then identify three modalities (egocentric RGB, eye gaze, head pose) that can be used to solve the task, and present a flexible transformer model that performs the task using these modalities, either individually or combined. We show that these modalities are relevant and complementary to the task, and investigate how to efficiently and effectively encode each modality. Additionally, we show the usefulness of this dataset towards classifying types of reading, extending current reading understanding studies conducted in constrained settings to larger scale, diversity and realism. Code, model, and data will be public.

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions—including a novel “expert commentary” done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. https://ego-exo4d-data.org/

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

We present Ego-Exo4D, a diverse, large-scale multi-modal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured ego-centric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is un-precedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions-including a novel “expert commentary” done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community.

Humans can orient themselves in their 3D environments using simple 2D maps. Differently, algorithms for visual localization mostly rely on complex 3D point clouds that are expensive to build, store, and maintain over time. We bridge this gap by introducing OrienterNet, the first deep neural network that can localize an image with sub-meter accuracy using the same 2D semantic maps that humans use. OrienterNet estimates the location and orientation of a query image by matching a neural Bird's-Eye View with open and globally available maps from OpenStreetMap, enabling anyone to localize anywhere such maps are available. OrienterNet is supervised only by camera poses but learns to perform semantic matching with a wide range of map elements in an end-to-end manner. To enable this, we introduce a large crowd-sourced dataset of images captured across 12 cities from the diverse viewpoints of cars, bikes, and pedestrians. OrienterNet generalizes to new datasets and pushes the state of the art in both robotics and AR scenarios. The code is available at github.com/facebookresearch/OrienterNet.

We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing ego-centric benchmarks either capture single subject or indoor-only scenarios, which limit the generalization of computer vision algorithms for real-world applications. We propose a novel 3D capture setup to construct a comprehensive ego-centric multi-human benchmark in the wild with annotations to support diverse tasks such as human detection, tracking, 2D/3D pose estimation, and mesh recovery. We leverage consumer-grade wearable camera-equipped glasses for the egocentric view, which enables us to capture dynamic activities like playing tennis, fencing, volleyball, etc. Furthermore, our multi-view setup generates accurate 3D ground truth even under severe or complete occlusion. The dataset consists of more than 125k egocentric images, spanning diverse scenes with a particular focus on challenging and unchoreographed multi-human activities and fast-moving egocentric views. We rigorously evaluate existing state-of-the-art methods and highlight their limitations in the egocentric scenario, specifically on multi-human tracking. To address such limitations, we propose EgoFormer, a novel approach with a multi-stream transformer architecture and explicit 3D spatial reasoning to estimate and track the human pose. EgoFormer significantly outperforms prior art by 13.6% IDF1 on the EgoHumans dataset.

We introduce the Aria Digital Twin (ADT)1- an egocentric dataset captured using Aria glasses with extensive object, environment, and human level ground truth. This ADT release contains 200 sequences of real-world activities conducted by Aria wearers in two real indoor scenes with 398 object instances (344 stationary and 74 dynamic). Each sequence consists of: a) raw data of two monochrome camera streams, one RGB camera stream, two IMU streams; b) complete sensor calibration; c) ground truth data including continuous 6-degree-of-freedom (6DoF) poses of the Aria devices, object 6DoF poses, 3D eye gaze vectors, 3D human poses, 2D image segmentations, image depth maps; and d) photo-realistic synthetic renderings. To the best of our knowledge, there is no existing egocentric dataset with a level of accuracy, photo-realism and comprehensiveness comparable to ADT. By contributing ADT to the research community, our mission is to set a new standard for evaluation in the egocentric machine perception domain, which includes very challenging research problems such as 3D object detection and tracking, scene reconstruction and understanding, sim-to-real learning, human pose prediction - while also inspiring new machine perception tasks for augmented reality (AR) applications. To kick start exploration of the ADT research use cases, we evaluated several existing state-of-the-art methods for object detection, segmentation and image translation tasks that demonstrate the usefulness of ADT as a benchmarking dataset.

Multi-modal datasets in artificial intelligence (AI) often capture a third-person perspective, but our embodied human intelligence evolved with sensory input from the egocentric, first-person perspective. Towards embodied AI, we introduce the Egocentric Communications (EgoCom) dataset to advance the state-of-the-art in conversational AI, natural language, audio speech analysis, computer vision, and machine learning. EgoCom is a first-of-its-kind natural conversations dataset containing multi-modal human communication data captured simultaneously from the participants' egocentric perspectives. EgoCom includes 38.5 hours of synchronized embodied stereo audio, egocentric video with 240,000 ground-truth, time-stamped word-level transcriptions and speaker labels from 34 diverse speakers. We study baseline performance on two novel applications that benefit from embodied data: (1) predicting turn-taking in conversations and (2) multi-speaker transcription. For (1), we investigate Bayesian baselines to predict turn-taking within 5 percent of human performance. For (2), we use simultaneous egocentric capture to combine Google speech-to-text outputs, improving global transcription by 79 percent relative to a single perspective. Both applications exploit EgoCom's synchronous multi-perspective data to augment performance of embodied AI tasks.

This paper proposes a do-it-all neural model of human hands, named LISA. The model can capture accurate hand shape and appearance, generalize to arbitrary hand sub-jects, provide dense surface correspondences, be reconstructed from images in the wild, and can be easily an-imated. We train LISA by minimizing the shape and appearance losses on a large set of multi-view RGB image se-quences annotated with coarse 3D poses of the hand skele-ton. For a 3D point in the local hand coordinates, our model predicts the color and the signed distance with respect to each hand bone independently, and then combines the per-bone predictions using the predicted skinning weights. The shape, color, and pose representations are disentangled by design, enabling fine control of the selected hand param-eters. We experimentally demonstrate that LISA can ac-curately reconstruct a dynamic hand from monocular or multi-view sequences, achieving a noticeably higher qual-ity of reconstructed hand shapes compared to baseline approaches. Project page: https://www.iri.upc.edu/people/ecorona/lisa/.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet expressive representation that enables high-quality view synthesis and motion interpolation. Our approach takes the high quality and compactness of static neural radiance fields in a new direction: to a model-free, dynamic setting. At the core of our approach is a novel time-conditioned neural radiance field that represents scene dynamics using a set of compact latent codes. We are able to significantly boost the training speed and perceptual quality of the generated imagery by a novel hierarchical training scheme in combination with ray importance sampling. Our learned representation is highly compact and able to represent a 10 second 30 FPS multi-view video recording by 18 cameras with a model size of only 28MB. We demonstrate that our method can render high-fidelity wide-angle novel views at over 1K resolution, even for complex and dynamic scenes. We perform an extensive qualitative and quantitative evaluation that shows that our approach outperforms the state of the art. Project website: https://neural-3d-video.github.io/.

Learning geometry, motion, and appearance priors of object classes is important for the solution of a large variety of computer vision problems. While the majority of approaches has focused on static objects, dynamic objects, especially with controllable articulation, are less explored. We propose a novel approach for learning a representation of the geometry, appearance, and motion of a class of articulated objects given only a set of color images as input. In a self-supervised manner, our novel representation learns shape, appearance, and articulation codes that enable independent control of these semantic dimensions. Our model is trained end-to-end without requiring any articulation annotations. Experiments show that our approach performs well for different joint types, such as revolute and prismatic joints, as well as different combinations of these joints. Compared to state of the art that uses direct 3D supervision and does not output appearance, we recover more faithful geometry and appearance from 2D observations only. In addition, our representation enables a large variety of applications, such as few-shot reconstruction, the generation of novel articulations, and novel view-synthesis. Project page: https://weify627.github.io/nasam/.

We propose a method to estimate the bidirectional reflectance distribution function (BRDF) and shading of complete scenes under static illumination given the 3D scene geometry and a corresponding high dynamic range (HDR) video. By splitting the BRDF into its diffuse and non-diffuse parts we solve the estimation of each component separately. For the diffuse component, we sample the incident illumination at each point in the scene using Monte Carlo ray tracing, allowing us to factor the captured surface color into albedo and shading. We then use a novel ray tracing-based optimization strategy to estimate the non-diffuse parameters of the BRDF. In a variety of experiments, we demonstrate that our method efficiently generates realistic copies of the observed scenes.

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system relies on a deep learning front-end to detect 3D objects from a given RGB frame and associate them to a global object-based map using a graph neural network (GNN). Based on these frame-to-model associations, our back-end optimizes object bounding volumes, represented as super-quadrics, under multi-view geometry constraints and the object scale prior. We validate the proposed system on ScanNet where we show a significant improvement over existing RGB-only methods.

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers their location, pose and shape in a coarse to fine manner. Key to FroDO is to embed object shapes in a novel learnt shape space that allows seamless switching between sparse point cloud and dense DeepSDF decoding. Given an input sequence of localized RGB frames, FroDO first aggregates 2D detections to instantiate a 3D bounding box per object. A shape code is regressed using an encoder network before optimizing shape and pose further under the learnt shape priors using sparse or dense shape representations. The optimization uses multi-view geometric, photometric and silhouette losses. We evaluate on real-world datasets, including Pix3D, Redwood-OS, and ScanNet, for single-view, multi-view, and multi-object reconstruction.

We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed depth refinement architecture, predicts view-consistent disparity and occlusion maps that helps the fusion system to produce geometrically consistent reconstructions. We utilize 3D dilated convolutions in our proposed cost filtering network that yields better filtering while almost halving the computational cost in comparison to state of the art cost filtering architectures. For feature extraction we use the Vortex Pooling architecture. The proposed method achieves state of the art results in KITTI 2012, KITTI 2015 and ETH 3D stereo benchmarks. Finally, we demonstrate that our system is able to produce high fidelity 3D scene reconstructions that outperforms the state of the art stereo system.

Computer graphics, 3D computer vision and robotics communities have produced multiple approaches to representing 3D geometry for rendering and reconstruction. These provide trade-offs across fidelity, efficiency and compression capabilities. In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data. DeepSDF, like its classical counterpart, represents a shape's surface by a continuous volumetric field: the magnitude of a point in the field represents the distance to the surface boundary and the sign indicates whether the region is inside (-) or outside (+) of the shape, hence our representation implicitly encodes a shape's boundary as the zero-level-set of the learned function while explicitly representing the classification of space as being part of the shapes interior or not. While classical SDF's both in analytical or discretized voxel form typically represent the surface of a single shape, DeepSDF can represent an entire class of shapes. Furthermore, we show state-of-the-art performance for learned 3D shape representation and completion while reducing the model size by an order of magnitude compared with previous work.

We present an approach for interactively scanning highly reflective objects with a commodity RGBD sensor. In addition to shape, our approach models the surface light field, encoding scene appearance from all directions. By factoring the surface light field into view-independent and wavelength-independent components, we arrive at a representation that can be robustly estimated with IR-equipped commodity depth sensors, and achieves high quality results.

Planar reflective surfaces such as glass and mirrors are notoriously hard to reconstruct for most current 3D scanning techniques. When treated naïvely, they introduce duplicate scene structures, effectively destroying the reconstruction altogether. Our key insight is that an easy to identify structure attached to the scanner---in our case an AprilTag---can yield reliable information about the existence and the geometry of glass and mirror surfaces in a scene. We introduce a fully automatic pipeline that allows us to reconstruct the geometry and extent of planar glass and mirror surfaces while being able to distinguish between the two. Furthermore, our system can automatically segment observations of multiple reflective surfaces in a scene based on their estimated planes and locations. In the proposed setup, minimal additional hardware is needed to create high-quality results. We demonstrate this using reconstructions of several scenes with a variety of real mirrors and glass.

We present the first dense SLAM system capable of reconstructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sensors. Our DynamicFusion approach reconstructs scene geometry whilst simultaneously estimating a dense volumetric 6D motion field that warps the estimated geometry into a live frame. Like KinectFusion, our system produces increasingly denoised, detailed, and complete reconstructions as more measurements are fused, and displays the updated model in real time. Because we do not require a template or other prior scene model, the approach is applicable to a wide range of moving objects and scenes.

This work integrates visual and physical constraints to perform real-time depth-only tracking of articulated objects, with a focus on tracking a robot's manipulators and manipulation targets in realistic scenarios. As such, we extend DART, an existing visual articulated object tracker, to additionally avoid interpenetration of multiple interacting objects, and to make use of contact information collected via torque sensors or touch sensors. To achieve greater stability, the tracker uses a switching model to detect when an object is stationary relative to the table or relative to the palm and then uses information from multiple frames to converge to an accurate and stable estimate. Deviation from stable states is detected in order to remain robust to failed grasps and dropped objects. The tracker is integrated into a shared autonomy system in which it provides state estimates used by a grasp planner and the controller of two anthropomorphic hands. We demonstrate the advantages and performance of the tracking system in simulation and on a real robot. Qualitative results are also provided for a number of challenging manipulations that are made possible by the speed, accuracy, and stability of the tracking system.

We present the major advantages of a new 'object oriented' 3D SLAM paradigm, which takes full advantage in the loop of prior knowledge that many scenes consist of repeated, domain-specific objects and structures. As a hand-held depth camera browses a cluttered scene, real-time 3D object recognition and tracking provides 6DoF camera-object constraints which feed into an explicit graph of objects, continually refined by efficient pose-graph optimisation. This offers the descriptive and predictive power of SLAM systems which perform dense surface reconstruction, but with a huge representation compression. The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions. We demonstrate real-time incremental SLAM in large, cluttered environments, including loop closure, relocalisation and the detection of moved objects, and of course the generation of an object level scene description with the potential to enable interaction.

A single hand-held camera provides an easily accessible but potentially extremely powerful setup for augmented reality. Capabilities which previously required expensive and complicated infrastructure have gradually become possible from a live monocular video feed, such as accurate camera tracking and, most recently, dense 3D scene reconstruction. A new frontier is to work towards recovering the reflectance properties of general surfaces and the lighting configuration in a scene without the need for probes, omni-directional cameras or specialised light-field cameras. Specular lighting phenomena cause effects in a video stream which can lead current tracking and reconstruction algorithms to fail. However, the potential exists to measure and use these effects to estimate deeper physical details about an environment, enabling advanced scene understanding and more convincing AR. In this paper we present an algorithm for real-time surface light-field capture from a single hand-held camera, which is able to capture dense illumination information for general specular surfaces. Our system incorporates a guidance mechanism to help the user interactively during capture. We then split the light-field into its diffuse and specular components, and show that the specular component can be used for estimation of an environment map. This enables the convincing placement of an augmentation on a specular surface such as a shiny book, with realistic synthesized shadow, reflection and occlusion of specularities as the viewpoint changes. Our method currently works for planar scenes, but the surface light-field representation makes it ideal for future combination with dense 3D reconstruction methods.

DTAM is a system for real-time camera tracking and reconstruction which relies not on feature extraction but dense, every pixel methods. As a single hand-held RGB camera flies over a static scene, we estimate detailed textured depth maps at selected keyframes to produce a surface patchwork with millions of vertices. We use the hundreds of images available in a video stream to improve the quality of a simple photometric data term, and minimise a global spatially regularised energy functional in a novel non-convex optimisation framework. Interleaved, we track the camera's 6DOF motion precisely by frame-rate whole image alignment against the entire dense model. Our algorithms are highly parallelisable throughout and DTAM achieves real-time performance using current commodity GPU hardware. We demonstrate that a dense model permits superior tracking performance under rapid motion compared to a state of the art method using features; and also show the additional usefulness of the dense model for real-time scene interaction in a physics-enhanced augmented reality application.

We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real-time. The current sensor pose is simultaneously obtained by tracking the live depth frame relative to the global model using a coarse-to-fine iterative closest point (ICP) algorithm, which uses all of the observed depth data available. We demonstrate the advantages of tracking against the growing full surface model compared with frame-to-frame tracking, obtaining tracking and mapping results in constant time within room sized scenes with limited drift and high accuracy. We also show both qualitative and quantitative results relating to various aspects of our tracking and mapping system. Modelling of natural scenes, in real-time with only commodity sensor and GPU hardware, promises an exciting step forward in augmented reality (AR), in particular, it allows dense surfaces to be reconstructed in real-time, with a level of detail and robustness beyond any solution yet presented using passive computer vision.

KinectFusion enables a user holding and moving a standard Kinect camera to rapidly create detailed 3D reconstructions of an indoor scene. Only the depth data from Kinect is used to track the 3D pose of the sensor and reconstruct, geometrically precise, 3D models of the physical scene in real-time. The capabilities of KinectFusion, as well as the novel GPU-based pipeline are described in full. Uses of the core system for low-cost handheld scanning, and geometry-aware augmented reality and physics-based interactions are shown. Novel extensions to the core GPU pipeline demonstrate object segmentation and user interaction directly in front of the sensor, without degrading camera tracking or reconstruction. These extensions are used to enable real-time multi-touch interactions anywhere, allowing any planar or non-planar reconstructed physical surface to be appropriated for touch.

We present a method which enables rapid and dense reconstruction of scenes browsed by a single live camera. We take point-based real-time structure from motion (SFM) as our starting point, generating accurate 3D camera pose estimates and a sparse point cloud. Our main novel contribution is to use an approximate but smooth base mesh generated from the SFM to predict the view at a bundle of poses around automatically selected reference frames spanning the scene, and then warp the base mesh into highly accurate depth maps based on view-predictive optical flow and a constrained scene flow update. The quality of the resulting depth maps means that a convincing global scene model can be obtained simply by placing them side by side and removing overlapping regions. We show that a cluttered indoor environment can be reconstructed from a live hand-held camera in a few seconds, with all processing performed by current desktop hardware. Real-time monocular dense reconstruction opens up many application areas, and we demonstrate both real-time novel view synthesis and advanced augmented reality where augmentations interact physically with the 3D scene and are correctly clipped by occlusions.

The problem of how to acquire a model of a physical robot,which is fit for evolution of controllers that can subsequently be used to control that robot, is considered in the context of racing a radio-controlled toy car around a randomised track. Several modelling techniques are compared, and the specific properties of the acquired models that influence the quality of the evolved controller are discussed. As we aim tominimise the amount of domain knowledge used, we furtherinvestigate the relation between the assumptions about the modelled system made by particular modelling techniques and the suitability of the acquired models as bases for controller evolution. We find that none of the models acquired is good enough on its own, and that a key to evolving robustbehaviour is to evaluate controllers simultaneously on multiple models during evolution. Examples of successfully evolved racing control for the physical car are analysed.