The hypothesis that image datasets gathered online "in the wild" can produce biased object recognizers, e.g. preferring professional photography or certain viewing angles, is studied. A new "in the lab" data collection infrastructure is proposed consisting of a drone which captures images as it circles around objects. Crucially, the control provided by this setup and the natural camera shake inherent to flight mitigate many biases. It's inexpensive and easily replicable nature may also potentially lead to a scalable data collection effort by the vision community. The procedure's usefulness is demonstrated by creating a dataset of Objects Obtained With fLight (OOWL). Denoted as OOWL500, it contains 120,000 images of 500 objects and is the largest "in the lab" image dataset available when both number of classes and objects per class are considered. Furthermore, it has enabled several of new insights on object recognition. First, a novel adversarial attack strategy is proposed, where image perturbations are defined in terms of semantic properties such as camera shake and pose. Indeed, experiments have shown that ImageNet has considerable amounts of pose and professional photography bias. Second, it is used to show that the augmentation of in the wild datasets, such as ImageNet, with in the lab data, such as OOWL500, can significantly decrease these biases, leading to object recognizers of improved generalization. Third, the dataset is used to study questions on "best procedures" for dataset collection. It is revealed that data augmentation with synthetic images does not suffice to eliminate in the wild datasets biases, and that camera shake and pose diversity play a more important role in object recognition robustness than previously thought.
Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a novel class-incremental learning scheme with (a) a new distillation loss, termed global distillation, (b) a learning strategy to avoid overfitting to the most recent task, and (c) a confidence-based sampling method to effectively leverage unlabeled external data. Our experimental …
Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections
College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）
提出基于3D Gaussian Splatting的交互式分割方法Seg-Wild，通过多维特征嵌入和Spiky 3D Gaussian Cutter处理无约束图像中的瞬态遮挡，实现更优的野外场景分割与重建质量。
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究院）
We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recognition systems (i.e. 'shelf-supervised'). We first infer a volumetric representation in a canonical frame, along with the camera pose. We enforce the representation geometrically consistent with both appearance and masks, and also that the synthesized novel views are indistinguishable from image collections. The coarse volumetric prediction is then converted to a mesh-based repre…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
This paper presents a novel method for date estimation of historical photographs from archival sources. The main contribution is to formulate the date estimation as a retrieval task, where given a query, the retrieved images are ranked in terms of the estimated date similarity. The closer are their embedded representations the closer are their dates. Contrary to the traditional models that design a neural network that learns a classifier or a regressor, we propose a learning objective based on the nDCG ranking metric. We have experimentally evaluated the performance of the method in two differ…
We present a method to learn the 3D surface of objects directly from a collection of images. Previous work achieved this capability by exploiting additional manual annotation, such as object pose, 3D surface templates, temporal continuity of videos, manually selected landmarks, and foreground/background masks. In contrast, our method does not make use of any such annotation. Rather, it builds a generative model, a convolutional neural network, which, given a noise vector sample, outputs the 3D surface and texture of an object and a background image. These 3 components combined with an addition…
CUNY City College（纽约市立大学城市学院）；CUNY Graduate Center（纽约市立大学研究生中心）
In order to create an "in-the-wild" dataset of facial emotions with large number of balanced samples, this paper proposes a game-based data collection framework. The framework mainly include three components: a game engine, a game interface, and a data collection and evaluation module. We use a deep learning approach to build an emotion classifier as the game engine. Then a emotion web game to allow gamers to enjoy the games, while the data collection module obtains automatically-labelled emotion images. Using our game, we have collected more than 15,000 images within a month of the test run a…
Google（谷歌）；University of Maryland, College Park（马里兰大学帕克分校）
We present a method for joint alignment of sparse in-the-wild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large dataset of images of a single object category. However, neither of the above assumptions hold true for the long-tail of the objects present in the world. We present a self-supervised technique that directly optimizes on a sparse collection of images of a particular object/object category to obtain consistent dense correspondences across the collection. We use pairwise nearest neighbors obtained from deep features of a…
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multilayer perceptron to model the density and color of a scene as a function of 3D coordinates. While NeRF works well on images of static subjects captured under controlled settings, it is incapable of modeling many ubiquitous, real-world phenomena in uncontrolled images, such as variable illumination or transient occluders. We introduce a series of extensions to NeRF to address …
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in every new scenario, a task that is infeasible. However, sources such as e-commerce websites and field guides provide annotated images for many classes. In this work, we study fine-grained domain adaptation as a step towards overcoming the dataset shift between easily acquired annotated images and the real world. Adaptation has not been studied in the fine-gr…
TU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
The integration of information acquired with different modalities, spatial resolution and spectral bands has shown to improve predictive accuracies. Data fusion is therefore one of the key challenges in remote sensing. Most prior work focusing on multi-modal fusion, assumes that modalities are always available during inference. This assumption limits the applications of multi-modal models since in practice the data collection process is likely to generate data with missing, incomplete or corrupted modalities. In this paper, we show that Generative Adversarial Networks can be effectively used t…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Adobe Research（奥多比研究院）
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse problems involving lighting and material understanding remain too severely ill-posed to be solved with single-illumination datasets. To fill this gap, we introduce a new multi-illumination dataset of more than 1000 real scenes, each captured under 25 lighting conditions. We demonstrate the richness of this dataset by training state-of-the-art models for three chal…
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild
Meta Reality Labs Research（Meta现实实验室）；Stanford University（斯坦福大学）；Nanyang Technological University（南洋理工大学）；University of Tübingen（蒂宾根大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Tencent Youtu Lab（腾讯优图实验室）；Nanjing University of Science and Technology（南京理工大学）
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on local color appearance and suffer from ambiguous noise. To address such problem, this paper presents a novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling. Instead of using controlled environment, the proposed method implicitly disentangles ID-consistent and scene-specific face from unconstrained photo set. Specifically, to learn ID-consistent face, LAP adaptively agg…
While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identifies an important but long overlooked issue of existing visual emotion benchmarks in the form of dataset biases. We design a series of tests to show and measure how such dataset biases obstruct learning a generalizable emotion recognition model. Based on our analysis, we propose a webly supervised approach by leveraging a large quantity of stock image data. Our approach uses…
The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown. Moreover, when pictures are taken in the wild, this task becomes even more challenging due to the blur varying spatially and the occlusions between the object. Due to the complexity of the general image model we propose a novel convolutional network architecture which directly generates the sharp image.This network is built in three stages, and exploits the benefits of pyramid schemes often used in blind deconvolution. One of the main difficulties in training such a network is to design a suita…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））
Datasets that capture the connection between vision, language, and affection are limited, causing a lack of understanding of the emotional aspect of human intelligence. As a step in this direction, the ArtEmis dataset was recently introduced as a large-scale dataset of emotional reactions to images along with language explanations of these chosen emotions. We observed a significant emotional bias towards instance-rich emotions, making trained neural speakers less accurate in describing under-represented emotions. We show that collecting new data, in the same way, is not effective in mitigating…
University of California, Merced（加州大学默塞德分校）；NVIDIA（英伟达）；University of California, San Diego（加州大学圣地亚哥分校）
This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D keypoints, or camera pose for each video frame, we pose video-based reconstruction as a self-supervised online adaptation problem applied to any incoming test video. We first learn a category-specific 3D reconstruction model from a collection of single-view images of the same category that jointly predicts the shape, texture, and camera pose of an image. Then, at inference time, we adapt the model to a test video ov…
We present an approach for estimating the period with which an action is repeated in a video. The crux of the approach lies in constraining the period prediction module to use temporal self-similarity as an intermediate representation bottleneck that allows generalization to unseen repetitions in videos in the wild. We train this model, called Repnet, with a synthetic dataset that is generated from a large unlabeled video collection by sampling short clips of varying lengths and repeating them with different periods and counts. This combination of synthetic data and a powerful yet constrained …
University of Tübingen（图宾根大学）；Google Research（谷歌研究院）
Inverse rendering of an object under entirely unknown capture conditions is a fundamental challenge in computer vision and graphics. Neural approaches such as NeRF have achieved photorealistic results on novel view synthesis, but they require known camera poses. Solving this problem with unknown camera poses is highly challenging as it requires joint optimization over shape, radiance, and pose. This problem is exacerbated when the input images are captured in the wild with varying backgrounds and illuminations. Standard pose estimation techniques fail in such image collections in the wild due …
Due to the COVID-19 pandemic, wearing face masks has become a mandate in public places worldwide. Face masks occlude a significant portion of the facial region. Additionally, people wear different types of masks, from simple ones to ones with graphics and prints. These pose new challenges to face recognition algorithms. Researchers have recently proposed a few masked face datasets for designing algorithms to overcome the challenges of masked face recognition. However, existing datasets lack the cultural diversity and collection in the unrestricted settings. Country like India with attire diver…
Taking Language Embedded 3D Gaussian Splatting into the Wild
State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；Beihang University（北航大学）
FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management
Holcombe Department of Electrical and Computer Engineering, Clemson University（克莱姆森大学霍尔科姆电气与计算机工程系）；Pacific Southwest Research Station, U.S. Forest Services（美国林业局太平洋西南研究站）；School of Environmental and Forest Sciences, University of Washington（华盛顿大学环境与森林科学学院）；US Forest Service, Rocky Mountain Research Station, Fire Sciences Laboratory（美国林业局落基山研究站火灾科学实验室）；Department of Mechanical Engineering, Clemson University（克莱姆森大学机械工程系）；Department of Forest Management, University of Montana（蒙大拿大学森林管理系）
With the mass-market adoption of dual-camera mobile phones, leveraging stereo information in computer vision has become increasingly important. Current state-of-the-art methods utilize learning-based algorithms, where the amount and quality of training samples heavily influence results. Existing stereo image datasets are limited either in size or subject variety. Hence, algorithms trained on such datasets do not generalize well to scenarios encountered in mobile photography. We present Holopix50k, a novel in-the-wild stereo image dataset, comprising 49,368 image pairs contributed by users of t…
University of Science and Technology of China（中国科学技术大学）
Facial action unit recognition is an important task for facial analysis. Owing to the complex collection environment, facial action unit recognition in the wild is still challenging. The 3rd competition on affective behavior analysis in-the-wild (ABAW) has provided large amount of facial images with facial action unit annotations. In this paper, we introduce a facial action unit recognition method based on transfer learning. We first use available facial images with expression labels to train the feature extraction network. Then we fine-tune the network for facial action unit recognition.
University of Exeter（埃克塞特大学）；Imperial College London（伦敦帝国学院）；Foundation for Research and Technology-Hellas（希腊研究与技术基金会）
Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment. In this work, we propose DeepFaceFlow, a robust, fast, and highly-accurate framework for the dense estimation of 3D non-rigid facial flow between pairs of monocular images. Our DeepFaceFlow framework was trained and tested on two very large-scale facial video datasets, one of them of our own collection and annotation, with the aid of occlusion-aware and 3D-based loss function. We conduct …
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
The University of Hong Kong（香港大学）；Tampere University（坦佩雷大学）；The Chinese University of Hong Kong（香港中文大学）；Max-Planck Institute for Informatics（马克斯·普朗克信息学研究所）
University of Kansas（堪萨斯大学）；Ryerson University（瑞尔森大学）
Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition of fingerspelling can help resolve communication barriers when interacting with deaf people. The main challenges prevalent in fingerspelling recognition are the ambiguity in the gestures and strong articulation of the hands. The automatic recognition model should address high inter-class visual similarity and high intra-class variation in the gestures. Most of the existing research in fingerspelling recognition has fo…
Toyota Research Institute（丰田研究院）；Massachusetts Institute of Technology（麻省理工学院）
Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labelled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method. Our proposed 3D gaze model extends existing models to include temporal information and to directly output a…
Inria（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）
This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any assumption of a single dominant class. This is far more general than typical colocalization, cosegmentation, or weakly-supervised localization tasks. We tackle the discovery and localization problem using a part-based region matching approach: We use off-the-shelf region proposals to form a set of candidate bounding boxes for objects and object parts. These regi…
Google Research（谷歌研究院）；MIT（麻省理工学院）；Cornell Tech（康奈尔理工学院）；Cornell University（康奈尔大学）；Georgia Tech（佐治亚理工学院）
We propose im2nerf, a learning framework that predicts a continuous neural object representation given a single input image in the wild, supervised by only segmentation output from off-the-shelf recognition methods. The standard approach to constructing neural radiance fields takes advantage of multi-view consistency and requires many calibrated views of a scene, a requirement that cannot be satisfied when learning on large-scale image data in the wild. We take a step towards addressing this shortcoming by introducing a model that encodes the input image into a disentangled object representati…
Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；IntSig Information Co. Ltd（合合信息科技股份有限公司）
Driving in a state of drowsiness is a major cause of road accidents, resulting in tremendous damage to life and property. Developing robust, automatic, real-time systems that can infer drowsiness states of drivers has the potential of making life-saving impact. However, developing drowsiness detection systems that work well in real-world scenarios is challenging because of the difficulties associated with collecting high-volume realistic drowsy data and modeling the complex temporal dynamics of evolving drowsy states. In this paper, we propose a data collection protocol that involves outfittin…
Face recognition has achieved outstanding performance in the last decade with the development of deep learning techniques. Nowadays, the challenges in face recognition are related to specific scenarios, for instance, the performance under diverse image quality, the robustness for aging and edge cases of person age (children and elders), distinguishing of related identities. In this set of problems, recognizing children's faces is one of the most sensitive and important. One of the reasons for this problem is the existing bias towards adults in existing face datasets. In this work, we present a…
The Swiss AI Lab, IDSIA, University of Lugano (USI) & SUPSI（瑞士人工智能实验室 IDSIA，卢加诺大学 (USI) 与南瑞士应用科学与艺术大学 (SUPSI)）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学 (KAUST)）
We share our experience with the recently released WILDS benchmark, a collection of ten datasets dedicated to developing models and training strategies which are robust to domain shifts. Several experiments yield a couple of critical observations which we believe are of general interest for any future work on WILDS. Our study focuses on two datasets: iWildCam and FMoW. We show that (1) Conducting separate cross-validation for each evaluation metric is crucial for both datasets, (2) A weak correlation between validation and test performance might make model development difficult for iWildCam, (…
University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；Huazhong University of Science and Technology（华中科技大学）
Large-scale datasets have successively proven their fundamental importance in several research fields, especially for early progress in some emerging topics. In this paper, we focus on the problem of visual speech recognition, also known as lipreading, which has received increasing interest in recent years. We present a naturally-distributed large-scale benchmark for lip reading in the wild, named LRW-1000, which contains 1,000 classes with 718,018 samples from more than 2,000 individual speakers. Each class corresponds to the syllables of a Mandarin word composed of one or several Chinese cha…
University of Southern California（南加州大学）；Snap Inc.（Snap公司）
We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds. This enables various object-centric rendering applications such as novel-view synthesis, relighting, and harmonized background composition from challenging in-the-wild input. Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse for…
