Guillermo Garcia-Hernando

Silvan Weder, Guillermo Garcia-Hernando, Aron Monszpart et al.

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.

Eduardo Arnold, Jamie Wynn, Sara Vicente et al.

Can we relocalize in a scene represented by a single reference image? Standard visual relocalization requires hundreds of images and scale calibration to build a scene-specific 3D map. In contrast, we propose Map-free Relocalization, i.e., using only one photo of a scene to enable instant, metric scaled relocalization. Existing datasets are not suitable to benchmark map-free relocalization, due to their focus on large scenes or their limited variability. Thus, we have constructed a new dataset of 655 small places of interest, such as sculptures, murals and fountains, collected worldwide. Each place comes with a reference image to serve as a relocalization anchor, and dozens of query images with known, metric camera poses. The dataset features changing conditions, stark viewpoint changes, high variability across places, and queries with low to no visual overlap with the reference image. We identify two viable families of existing methods to provide baseline results: relative pose regression, and feature matching combined with single-image depth prediction. While these methods show reasonable performance on some favorable scenes in our dataset, map-free relocalization proves to be a challenge that requires new, innovative solutions.

Matias Turkulainen, Akshay Krishnan, Filippo Aleotti et al.

We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstructions require good camera coverage, but ground imagery is time-consuming and hard to capture at scale for large outdoor scenes. Fortunately, satellite imagery can provide a global geometric prior that is easy to access via public APIs. Cross-View Splatter fuses orthorectified satellite views with GPS-tagged ground photos to predict Gaussian splats in a unified 3D coordinate frame. By aligning ground and bird's-eye feature representations, our model improves scene coverage and novel-view synthesis, compared to ground imagery alone. We train on curated georeferenced datasets and paired satellite-terrain data, mined from open mapping services. We evaluate our method on a new benchmark for novel-view synthesis with georeferenced imagery allowing comparison to prior state-of-the-art methods. Our code and data preparation will be available at https://nianticspatial.github.io/cross-view-splatter/.

Eugene Valassakis, Guillermo Garcia-Hernando

Predicting camera-space hand meshes from single RGB images is crucial for enabling realistic hand interactions in 3D virtual and augmented worlds. Previous work typically divided the task into two stages: given a cropped image of the hand, predict meshes in relative coordinates, followed by lifting these predictions into camera space in a separate and independent stage, often resulting in the loss of valuable contextual and scale information. To prevent the loss of these cues, we propose unifying these two stages into an end-to-end solution that addresses the 2D-3D correspondence problem. This solution enables back-propagation from camera space outputs to the rest of the network through a new differentiable global positioning module. We also introduce an image rectification step that harmonizes both the training dataset and the input image as if they were acquired with the same camera, helping to alleviate the inherent scale-depth ambiguity of the problem. We validate the effectiveness of our framework in evaluations against several baselines and state-of-the-art approaches across three public benchmarks.

Sergio Izquierdo, Mohamed Sayed, Michael Firman et al.

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.

Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson et al.

We introduce the novel task of Language-Guided Object Placement in Real 3D Scenes. Our model is given a 3D scene's point cloud, a 3D asset, and a textual prompt broadly describing where the 3D asset should be placed. The task here is to find a valid placement for the 3D asset that respects the prompt. Compared with other language-guided localization tasks in 3D scenes such as grounding, this task has specific challenges: it is ambiguous because it has multiple valid solutions, and it requires reasoning about 3D geometric relationships and free space. We inaugurate this task by proposing a new benchmark and evaluation protocol. We also introduce a new dataset for training 3D LLMs on this task, as well as the first method to serve as a non-trivial baseline. We believe that this challenging task and our new benchmark could become part of the suite of benchmarks used to evaluate and compare generalist 3D LLM models.

Mohamed Sayed, Filippo Aleotti, Jamie Watson et al.

Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contrast, our model leverages historical predictions by giving the latest 3D geometry data as an extra input to our network. This self-generated geometric hint can encode information from areas of the scene not covered by the keyframes and it is more regularized when compared to individual predicted depth maps for previous frames. We introduce a Hint MLP which combines cost volume features with a hint of the prior geometry, rendered as a depth map from the current camera location, together with a measure of the confidence in the prior geometry. We demonstrate that our method, which can run at interactive speeds, achieves state-of-the-art estimates of depth and 3D scene reconstruction in both offline and incremental evaluation scenarios.

Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov et al.

To what extent are two images picturing the same 3D surfaces? Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching and geometric verification of large sets of local features. This expense is further multiplied when a query image is evaluated against a gallery, e.g. in visual relocalization. While we don't obviate the need for geometric verification, we propose an interpretable image-embedding that cuts the search in scale space to essentially a lookup. Our approach measures the asymmetric relation between two images. The model then learns a scene-specific measure of similarity, from training examples with known 3D visible-surface overlaps. The result is that we can quickly identify, for example, which test image is a close-up version of another, and by what scale factor. Subsequently, local features need only be detected at that scale. We validate our scene-specific model by showing how this embedding yields competitive image-matching results, while being simpler, faster, and also interpretable by humans.

Guillermo Garcia-Hernando, Edward Johns, Tae-Kyun Kim

Dexterous manipulation of objects in virtual environments with our bare hands, by using only a depth sensor and a state-of-the-art 3D hand pose estimator (HPE), is challenging. While virtual environments are ruled by physics, e.g. object weights and surface frictions, the absence of force feedback makes the task challenging, as even slight inaccuracies on finger tips or contact points from HPE may make the interactions fail. Prior arts simply generate contact forces in the direction of the fingers' closures, when finger joints penetrate virtual objects. Although useful for simple grasping scenarios, they cannot be applied to dexterous manipulations such as in-hand manipulation. Existing reinforcement learning (RL) and imitation learning (IL) approaches train agents that learn skills by using task-specific rewards, without considering any online user input. In this work, we propose to learn a model that maps noisy input hand poses to target virtual poses, which introduces the needed contacts to accomplish the tasks on a physics simulator. The agent is trained in a residual setting by using a model-free hybrid RL+IL approach. A 3D hand pose estimation reward is introduced leading to an improvement on HPE accuracy when the physics-guided corrected target poses are remapped to the input space. As the model corrects HPE errors by applying minor but crucial joint displacements for contacts, this helps to keep the generated motion visually close to the user input. Since HPE sequences performing successful virtual interactions do not exist, a data generation scheme to train and evaluate the system is proposed. We test our framework in two applications that use hand pose estimates for dexterous manipulations: hand-object interactions in VR and hand-object motion reconstruction in-the-wild.

Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek et al.

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set. Unfortunately, since the space of hand poses is highly dimensional, it is inherently not feasible to cover the whole space densely, despite recent efforts in collecting large-scale training datasets. This sampling problem is even more severe when hands are interacting with objects and/or inputs are RGB rather than depth images, as RGB images also vary with lighting conditions and colors. To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. More exactly, HANDS'19 is designed (a) to evaluate the influence of both depth and color modalities on 3D hand pose estimation, under the presence or absence of objects; (b) to assess the generalisation abilities w.r.t. four main axes: shapes, articulations, viewpoints, and objects; (c) to explore the use of a synthetic hand model to fill the gaps of current datasets. Through the challenge, the overall accuracy has dramatically improved over the baseline, especially on extrapolation tasks, from 27mm to 13mm mean joint error. Our analyses highlight the impacts of: Data pre-processing, ensemble approaches, the use of a parametric 3D hand model (MANO), and different HPE methods/backbones.

Juil Sock, Guillermo Garcia-Hernando, Anil Armagan et al.

Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common workaround is to generate and train on synthetic scenes, with the drawback of limited generalisation when the model is deployed in the real world. In this work, a two-stage 6D object pose estimator framework that can be applied on top of existing neural-network-based approaches and that does not require pose annotations on real images is proposed. The first self-supervised stage enforces the pose consistency between rendered predictions and real input images, narrowing the gap between the two domains. The second stage fine-tunes the previously trained model by enforcing the photometric consistency between pairs of different object views, where one image is warped and aligned to match the view of the other and thus enabling their comparison. In the absence of both real image annotations and depth information, applying the proposed framework on top of two recent approaches results in state-of-the-art performance when compared to methods trained only on synthetic data, domain adaptation baselines and a concurrent self-supervised approach on LINEMOD, LINEMOD OCCLUSION and HomebrewedDB datasets.

Caner Sahin, Guillermo Garcia-Hernando, Juil Sock et al.

Object pose recovery has gained increasing attention in the computer vision field as it has become an important problem in rapidly evolving technological areas related to autonomous driving, robotics, and augmented reality. Existing review-related studies have addressed the problem at visual level in 2D, going through the methods which produce 2D bounding boxes of objects of interest in RGB images. The 2D search space is enlarged either using the geometry information available in the 3D space along with RGB (Mono/Stereo) images, or utilizing depth data from LIDAR sensors and/or RGB-D cameras. 3D bounding box detectors, producing category-level amodal 3D bounding boxes, are evaluated on gravity aligned images, while full 6D object pose estimators are mostly tested at instance-level on the images where the alignment constraint is removed. Recently, 6D object pose estimation is tackled at the level of categories. In this paper, we present the first comprehensive and most recent review of the methods on object pose recovery, from 3D bounding box detectors to full 6D pose estimators. The methods mathematically model the problem as a classification, regression, classification & regression, template matching, and point-pair feature matching task. Based on this, a mathematical-model-based categorization of the methods is established. Datasets used for evaluating the methods are investigated with respect to the challenges, and evaluation metrics are studied. Quantitative results of experiments in the literature are analyzed to show which category of methods best performs across what types of challenges. The analyses are further extended comparing two methods, which are our own implementations, so that the outcomes from the public results are further solidified. Current position of the field is summarized regarding object pose recovery, and possible research directions are identified.

Juil Sock, Guillermo Garcia-Hernando, Tae-Kyun Kim

In this work, we explore how a strategic selection of camera movements can facilitate the task of 6D multi-object pose estimation in cluttered scenarios while respecting real-world constraints important in robotics and augmented reality applications, such as time and distance traveled. In the proposed framework, a set of multiple object hypotheses is given to an agent, which is inferred by an object pose estimator and subsequently spatio-temporally selected by a fusion function that makes use of a verification score that circumvents the need of ground-truth annotations. The agent reasons about these hypotheses, directing its attention to the object which it is most uncertain about, moving the camera towards such an object. Unlike previous works that propose short-sighted policies, our agent is trained in simulated scenarios using reinforcement learning, attempting to learn the camera moves that produce the most accurate object poses hypotheses for a given temporal and spatial budget, without the need of viewpoints rendering during inference. Our experiments show that the proposed approach successfully estimates the 6D object pose of a stack of objects in both challenging cluttered synthetic and real scenarios, showing superior performance compared to strong baselines.

Caner Sahin, Guillermo Garcia-Hernando, Juil Sock et al.

6D object pose estimation is an important task that determines the 3D position and 3D rotation of an object in camera-centred coordinates. By utilizing such a task, one can propose promising solutions for various problems related to scene understanding, augmented reality, control and navigation of robotics. Recent developments on visual depth sensors and low-cost availability of depth data significantly facilitate object pose estimation. Using depth information from RGB-D sensors, substantial progress has been made in the last decade by the methods addressing the challenges such as viewpoint variability, occlusion and clutter, and similar looking distractors. Particularly, with the recent advent of convolutional neural networks, RGB-only based solutions have been presented. However, improved results have only been reported for recovering the pose of known instances, i.e., for the instance-level object pose estimation tasks. More recently, state-of-the-art approaches target to solve object pose estimation problem at the level of categories, recovering the 6D pose of unknown instances. To this end, they address the challenges of the category-level tasks such as distribution shift among source and target domains, high intra-class variations, and shape discrepancies between objects.

Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao et al.

This report outlines the proceedings of the Fourth International Workshop on Observing and Understanding Hands in Action (HANDS 2018). The fourth instantiation of this workshop attracted significant interest from both academia and the industry. The program of the workshop included regular papers that are published as the workshop's proceedings, extended abstracts, invited posters, and invited talks. Topics of the submitted works and invited talks and posters included novel methods for hand pose estimation from RGB, depth, or skeletal data, datasets for special cases and real-world applications, and techniques for hand motion re-targeting and hand gesture recognition. The invited speakers are leaders in their respective areas of specialization, coming from both industry and academia. The main conclusions that can be drawn are the turn of the community towards RGB data and the maturation of some methods and techniques, which in turn has led to increasing interest for real-world applications.

Dafni Antotsiou, Guillermo Garcia-Hernando, Tae-Kyun Kim

Human hand actions are quite complex, especially when they involve object manipulation, mainly due to the high dimensionality of the hand and the vast action space that entails. Imitating those actions with dexterous hand models involves different important and challenging steps: acquiring human hand information, retargeting it to a hand model, and learning a policy from acquired data. In this work, we capture the hand information by using a state-of-the-art hand pose estimator. We tackle the retargeting problem from the hand pose to a 29 DoF hand model by combining inverse kinematics and PSO with a task objective optimisation. This objective encourages the virtual hand to accomplish the manipulation task, relieving the effect of the estimator's noise and the domain gap. Our approach leads to a better success rate in the grasping task compared to our inverse kinematics baseline, allowing us to record successful human demonstrations. Furthermore, we used these demonstrations to learn a policy network using generative adversarial imitation learning (GAIL) that is able to autonomously grasp an object in the virtual space.

Shanxin Yuan, Guillermo Garcia-Hernando, Bjorn Stenger et al.

In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate the top 10 state-of-the-art methods on three tasks: single frame 3D pose estimation, 3D hand tracking, and hand pose estimation during object interaction. We analyze the performance of different CNN structures with regard to hand shape, joint visibility, view point and articulation distributions. Our findings include: (1) isolated 3D hand pose estimation achieves low mean errors (10 mm) in the view point range of [70, 120] degrees, but it is far from being solved for extreme view points; (2) 3D volumetric representations outperform 2D CNNs, better capturing the spatial structure of the depth data; (3) Discriminative methods still generalize poorly to unseen hand shapes; (4) While joint occlusions pose a challenge for most methods, explicit modeling of structure constraints can significantly narrow the gap between errors on visible and occluded joints.

Shanxin Yuan, Qi Ye, Guillermo Garcia-Hernando et al.

We present the 2017 Hands in the Million Challenge, a public competition designed for the evaluation of the task of 3D hand pose estimation. The goal of this challenge is to assess how far is the state of the art in terms of solving the problem of 3D hand pose estimation as well as detect major failure and strength modes of both systems and evaluation metrics that can help to identify future research directions. The challenge follows up the recent publication of BigHand2.2M and First-Person Hand Action datasets, which have been designed to exhaustively cover multiple hand, viewpoint, hand articulation, and occlusion. The challenge consists of a standardized dataset, an evaluation protocol for two different tasks, and a public competition. In this document we describe the different aspects of the challenge and, jointly with the results of the participants, it will be presented at the 3rd International Workshop on Observing and Understanding Hands in Action, HANDS 2017, with ICCV 2017.

Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek et al.

In this work we study the use of 3D hand poses to recognize first-person dynamic hand actions interacting with 3D objects. Towards this goal, we collected RGB-D video sequences comprised of more than 100K frames of 45 daily hand action categories, involving 26 different objects in several hand configurations. To obtain hand pose annotations, we used our own mo-cap system that automatically infers the 3D location of each of the 21 joints of a hand model via 6 magnetic sensors and inverse kinematics. Additionally, we recorded the 6D object poses and provide 3D object models for a subset of hand-object interaction sequences. To the best of our knowledge, this is the first benchmark that enables the study of first-person hand actions with the use of 3D hand poses. We present an extensive experimental evaluation of RGB-D and pose-based action recognition by 18 baselines/state-of-the-art approaches. The impact of using appearance features, poses, and their combinations are measured, and the different training/testing protocols are evaluated. Finally, we assess how ready the 3D hand pose estimation field is when hands are severely occluded by objects in egocentric views and its influence on action recognition. From the results, we see clear benefits of using hand pose as a cue for action recognition compared to other data modalities. Our dataset and experiments can be of interest to communities of 3D hand pose estimation, 6D object pose, and robotics as well as action recognition.

Guillermo Garcia-Hernando, Tae-Kyun Kim

A human action can be seen as transitions between one's body poses over time, where the transition depicts a temporal relation between two poses. Recognizing actions thus involves learning a classifier sensitive to these pose transitions as well as to static poses. In this paper, we introduce a novel method called transitions forests, an ensemble of decision trees that both learn to discriminate static poses and transitions between pairs of two independent frames. During training, node splitting is driven by alternating two criteria: the standard classification objective that maximizes the discrimination power in individual frames, and the proposed one in pairwise frame transitions. Growing the trees tends to group frames that have similar associated transitions and share same action label incorporating temporal information that was not available otherwise. Unlike conventional decision trees where the best split in a node is determined independently of other nodes, the transition forests try to find the best split of nodes jointly (within a layer) for incorporating distant node transitions. When inferring the class label of a new frame, it is passed down the trees and the prediction is made based on previous frame predictions and the current one in an efficient and online manner. We apply our method on varied skeleton action recognition and online detection datasets showing its suitability over several baselines and state-of-the-art approaches.