Ales Leonardis

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai et al.

Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks. These are typically not compared nor discussed in the literature due to a lack of multi-modal datasets. Texture-less regions are problematic for structure from motion and stereo, reflective material poses issues for active sensing, and distances for translucent objects are intricate to measure with existing hardware. Training on inaccurate or corrupt data induces model bias and hampers generalisation capabilities. These effects remain unnoticed if the sensor measurement is considered as ground truth during the evaluation. This paper investigates the effect of sensor errors for the dense 3D vision tasks of depth estimation and reconstruction. We rigorously show the significant impact of sensor characteristics on the learned predictions and notice generalisation issues arising from various technologies in everyday household environments. For evaluation, we introduce a carefully designed dataset\footnote{dataset available at https://github.com/Junggy/HAMMER-dataset} comprising measurements from commodity sensors, namely D-ToF, I-ToF, passive/active stereo, and monocular RGB+P. Our study quantifies the considerable sensor noise impact and paves the way to improved dense vision estimates and targeted data fusion.

Tze Ho Elden Tse, Kwang In Kim, Ales Leonardis et al.

Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object reconstruction require explicitly defined physical constraints and known objects, which limits its application domains. Our algorithm is agnostic to object models, and it learns the physical rules governing hand-object interaction. This requires automatically inferring the shapes and physical interaction of hands and (potentially unknown) objects. We seek to approach this challenging problem by proposing a collaborative learning strategy where two-branches of deep networks are learning from each other. Specifically, we transfer hand mesh information to the object branch and vice versa for the hand branch. The resulting optimisation (training) problem can be unstable, and we address this via two strategies: (i) attention-guided graph convolution which helps identify and focus on mutual occlusion and (ii) unsupervised associative loss which facilitates the transfer of information between the branches. Experiments using four widely-used benchmarks show that our framework achieves beyond state-of-the-art accuracy in 3D pose estimation, as well as recovers dense 3D hand and object shapes. Each technical component above contributes meaningfully in the ablation study.

Linfang Zheng, Chen Wang, Yinghan Sun et al.

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object's size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. The proposed HS-layer: 1) is able to perceive local-global geometric structure and global information, 2) is robust to noise, and 3) can encode size and translation information. Our experiments show that the simple replacement of the 3D-GC layer with the proposed HS-layer on the baseline method (GPV-Pose) achieves a significant improvement, with the performance increased by 14.5% on 5d2cm metric and 10.3% on IoU75. Our method outperforms the state-of-the-art methods by a large margin (8.3% on 5d2cm, 6.9% on IoU75) on the REAL275 dataset and runs in real-time (50 FPS).

Xue Hu, Xinghui Li, Benjamin Busam et al. · oxford

For visual manipulation tasks, we aim to represent image content with semantically meaningful features. However, learning implicit representations from images often lacks interpretability, especially when attributes are intertwined. We focus on the challenging task of extracting disentangled 3D attributes only from 2D image data. Specifically, we focus on human appearance and learn implicit pose, shape and garment representations of dressed humans from RGB images. Our method learns an embedding with disentangled latent representations of these three image properties and enables meaningful re-assembling of features and property control through a 2D-to-3D encoder-decoder structure. The 3D model is inferred solely from the feature map in the learned embedding space. To the best of our knowledge, our method is the first to achieve cross-domain disentanglement for this highly under-constrained problem. We qualitatively and quantitatively demonstrate our framework's ability to transfer pose, shape, and garments in 3D reconstruction on virtual data and show how an implicit shape loss can benefit the model's ability to recover fine-grained reconstruction details.

Jiali Zheng, Youngkyoon Jang, Athanasios Papaioannou et al.

This paper introduces the Imperial Light-Stage Head (ILSH) dataset, a novel light-stage-captured human head dataset designed to support view synthesis academic challenges for human heads. The ILSH dataset is intended to facilitate diverse approaches, such as scene-specific or generic neural rendering, multiple-view geometry, 3D vision, and computer graphics, to further advance the development of photo-realistic human avatars. This paper details the setup of a light-stage specifically designed to capture high-resolution (4K) human head images and describes the process of addressing challenges (preprocessing, ethical issues) in collecting high-quality data. In addition to the data collection, we address the split of the dataset into train, validation, and test sets. Our goal is to design and support a fair view synthesis challenge task for this novel dataset, such that a similar level of performance can be maintained and expected when using the test set, as when using the validation set. The ILSH dataset consists of 52 subjects captured using 24 cameras with all 82 lighting sources turned on, resulting in a total of 1,248 close-up head images, border masks, and camera pose pairs.

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai et al.

Depth estimation is a core task in 3D computer vision. Recent methods investigate the task of monocular depth trained with various depth sensor modalities. Every sensor has its advantages and drawbacks caused by the nature of estimates. In the literature, mostly mean average error of the depth is investigated and sensor capabilities are typically not discussed. Especially indoor environments, however, pose challenges for some devices. Textureless regions pose challenges for structure from motion, reflective materials are problematic for active sensing, and distances for translucent material are intricate to measure with existing sensors. This paper proposes HAMMER, a dataset comprising depth estimates from multiple commonly used sensors for indoor depth estimation, namely ToF, stereo, structured light together with monocular RGB+P data. We construct highly reliable ground truth depth maps with the help of 3D scanners and aligned renderings. A popular depth estimators is trained on this data and typical depth senosors. The estimates are extensively analyze on different scene structures. We notice generalization issues arising from various sensor technologies in household environments with challenging but everyday scene content. HAMMER, which we make publicly available, provides a reliable base to pave the way to targeted depth improvements and sensor fusion approaches.

Richard Shaw, Sibi Catley-Chandar, Ales Leonardis et al.

Reconstruction of high-quality HDR images is at the core of modern computational photography. Significant progress has been made with multi-frame HDR reconstruction methods, producing high-resolution, rich and accurate color reconstructions with high-frequency details. However, they are still prone to fail in dynamic or largely over-exposed scenes, where frame misalignment often results in visible ghosting artifacts. Recent approaches attempt to alleviate this by utilizing an event-based camera (EBC), which measures only binary changes of illuminations. Despite their desirable high temporal resolution and dynamic range characteristics, such approaches have not outperformed traditional multi-frame reconstruction methods, mainly due to the lack of color information and low-resolution sensors. In this paper, we propose to leverage both bracketed LDR images and simultaneously captured events to obtain the best of both worlds: high-quality RGB information from bracketed LDRs and complementary high frequency and dynamic range information from events. We present a multi-modal end-to-end learning-based HDR imaging system that fuses bracketed images and event modalities in the feature domain using attention and multi-scale spatial alignment modules. We propose a novel event-to-image feature distillation module that learns to translate event features into the image-feature space with self-supervision. Our framework exploits the higher temporal resolution of events by sub-sampling the input event streams using a sliding window, enriching our combined feature representation. Our proposed approach surpasses SoTA multi-frame HDR reconstruction methods using synthetic and real events, with a 2dB and 1dB improvement in PSNR-L and PSNR-mu on the HdM HDR dataset, respectively.

Wei-Hong Li, Steven McDonagh, Ales Leonardis et al.

Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations in high dimensional feature space across tasks. However, the cross-task correlations that are learned in the unstructured feature space can be extremely noisy and susceptible to overfitting, consequently hurting performance. We propose to address this problem by introducing a structured 3D-aware regularizer which interfaces multiple tasks through the projection of features extracted from an image encoder to a shared 3D feature space and decodes them into their task output space through differentiable rendering. We show that the proposed method is architecture agnostic and can be plugged into various prior multi-task backbones to improve their performance; as we evidence using standard benchmarks NYUv2 and PASCAL-Context.

Alexander Krull, Hector Basevi, Benjamin Salmon et al.

We present a fresh perspective on shot noise corrupted images and noise removal. By viewing image formation as the sequential accumulation of photons on a detector grid, we show that a network trained to predict where the next photon could arrive is in fact solving the minimum mean square error (MMSE) denoising task. This new perspective allows us to make three contributions: We present a new strategy for self-supervised denoising, We present a new method for sampling from the posterior of possible solutions by iteratively sampling and adding small numbers of photons to the image. We derive a full generative model by starting this process from an empty canvas. We call this approach generative accumulation of photons (GAP). We evaluate our method quantitatively and qualitatively on 4 new fluorescence microscopy datasets, which will be made available to the community. We find that it outperforms supervised, self-supervised and unsupervised baselines or performs on-par.

Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim et al.

Despite the recent efforts in accurate 3D annotations in hand and object datasets, there still exist gaps in 3D hand and object reconstructions. Existing works leverage contact maps to refine inaccurate hand-object pose estimations and generate grasps given object models. However, they require explicit 3D supervision which is seldom available and therefore, are limited to constrained settings, e.g., where thermal cameras observe residual heat left on manipulated objects. In this paper, we propose a novel semi-supervised framework that allows us to learn contact from monocular images. Specifically, we leverage visual and geometric consistency constraints in large-scale datasets for generating pseudo-labels in semi-supervised learning and propose an efficient graph-based network to infer contact. Our semi-supervised learning framework achieves a favourable improvement over the existing supervised learning methods trained on data with `limited' annotations. Notably, our proposed model is able to achieve superior results with less than half the network parameters and memory access cost when compared with the commonly-used PointNet-based approach. We show benefits from using a contact map that rules hand-object interactions to produce more accurate reconstructions. We further demonstrate that training with pseudo-labels can extend contact map estimations to out-of-domain objects and generalise better across multiple datasets.

Nanqing Dong, Linus Ericsson, Yongxin Yang et al.

Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn transferable representations for downstream detection tasks. This leads to the necessity of training multiple detection-specific modules from scratch in the fine-tuning phase. We argue that the region proposal network (RPN), a common detection-specific module, can additionally be pre-trained towards reducing the localization error of multi-stage detectors. In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance. We evaluate the efficacy of our approach on benchmark object detection tasks and additional downstream tasks, including instance segmentation and few-shot detection. In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance, with largest gains found in label-scarce settings.

William Thong, Jose Costa Pereira, Sarah Parisot et al.

Image quality assessment (IQA) forms a natural and often straightforward undertaking for humans, yet effective automation of the task remains highly challenging. Recent metrics from the deep learning community commonly compare image pairs during training to improve upon traditional metrics such as PSNR or SSIM. However, current comparisons ignore the fact that image content affects quality assessment as comparisons only occur between images of similar content. This restricts the diversity and number of image pairs that the model is exposed to during training. In this paper, we strive to enrich these comparisons with content diversity. Firstly, we relax comparison constraints, and compare pairs of images with differing content. This increases the variety of available comparisons. Secondly, we introduce listwise comparisons to provide a holistic view to the model. By including differentiable regularizers, derived from correlation coefficients, models can better adjust predicted scores relative to one another. Evaluation on multiple benchmarks, covering a wide range of distortions and image content, shows the effectiveness of our learning scheme for training image quality assessment models.

Michal Nazarczuk, Sibi Catley-Chandar, Ales Leonardis et al.

Recent High Dynamic Range (HDR) techniques extend the capabilities of current cameras where scenes with a wide range of illumination can not be accurately captured with a single low-dynamic-range (LDR) image. This is generally accomplished by capturing several LDR images with varying exposure values whose information is then incorporated into a merged HDR image. While such approaches work well for static scenes, dynamic scenes pose several challenges, mostly related to the difficulty of finding reliable pixel correspondences. Data-driven approaches tackle the problem by learning an end-to-end mapping with paired LDR-HDR training data, but in practice generating such HDR ground-truth labels for dynamic scenes is time-consuming and requires complex procedures that assume control of certain dynamic elements of the scene (e.g. actor pose) and repeatable lighting conditions (stop-motion capturing). In this work, we propose a novel self-supervised approach for learnable HDR estimation that alleviates the need for HDR ground-truth labels. We propose to leverage the internal statistics of LDR images to create HDR pseudo-labels. We separately exploit static and well-exposed parts of the input images, which in conjunction with synthetic illumination clipping and motion augmentation provide high quality training examples. Experimental results show that the HDR models trained using our proposed self-supervision approach achieve performance competitive with those trained under full supervision, and are to a large extent superior to previous methods that equally do not require any supervision.

Hao Ai, Wenjie Chang, Jianbo Jiao et al.

Articulated objects are ubiquitous in daily life. Our goal is to achieve a high-quality reconstruction, segmentation of independent moving parts, and analysis of articulation. Recent methods analyse two different articulation states and perform per-point part segmentation, optimising per-part articulation using cross-state correspondences, given a priori knowledge of the number of parts. Such assumptions greatly limit their applications and performance. Their robustness is reduced when objects cannot be clearly visible in both states. To address these issues, in this paper, we present a new framework, Articulation in Motion (AiM). We infer part-level decomposition, articulation kinematics, and reconstruct an interactive 3D digital replica from a user-object interaction video and a start-state scan. We propose a dual-Gaussian scene representation that is learned from an initial 3DGS scan of the object and a video that shows the movement of separate parts. It uses motion cues to segment the object into parts and assign articulation joints. Subsequently, a robust, sequential RANSAC is employed to achieve part mobility analysis without any part-level structural priors, which clusters moving primitives into rigid parts and estimates kinematics while automatically determining the number of parts. The proposed approach separates the object into parts, each represented as a 3D Gaussian set, enabling high-quality rendering. Our approach yields higher quality part segmentation than previous methods, without prior knowledge. Extensive experimental analysis on both simple and complex objects validates the effectiveness and strong generalisation ability of our approach. Project page: https://haoai-1997.github.io/AiM/.

Wei Chen, Xi Jia, Zhongqun Zhang et al.

In this paper, we propose a novel 3D graph convolution based pipeline for category-level 6D pose and size estimation from monocular RGB-D images. The proposed method leverages an efficient 3D data augmentation and a novel vector-based decoupled rotation representation. Specifically, we first design an orientation-aware autoencoder with 3D graph convolution for latent feature learning. The learned latent feature is insensitive to point shift and size thanks to the shift and scale-invariance properties of the 3D graph convolution. Then, to efficiently decode the rotation information from the latent feature, we design a novel flexible vector-based decomposable rotation representation that employs two decoders to complementarily access the rotation information. The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task. Finally, we propose a 3D deformation mechanism to increase the generalization ability of the pipeline. Extensive experiments show that the proposed pipeline achieves state-of-the-art performance on category-level tasks. Further, the experiments demonstrate that the proposed rotation representation is more suitable for the pose estimation tasks than other rotation representations.

Liqiong Wang, Teng Jin, Jinyu Yang et al.

In the general domain, large multimodal models (LMMs) have achieved significant advancements, yet challenges persist in applying them to specific fields, especially agriculture. As the backbone of the global economy, agriculture confronts numerous challenges, with pests and diseases being particularly concerning due to their complexity, variability, rapid spread, and high resistance. This paper specifically addresses these issues. We construct the first multimodal instruction-following dataset in the agricultural domain, covering over 221 types of pests and diseases with approximately 400,000 data entries. This dataset aims to explore and address the unique challenges in pest and disease control. Based on this dataset, we propose a knowledge-infused training method to develop Agri-LLaVA, an agricultural multimodal conversation system. To accelerate progress in this field and inspire more researchers to engage, we design a diverse and challenging evaluation benchmark for agricultural pests and diseases. Experimental results demonstrate that Agri-LLaVA excels in agricultural multimodal conversation and visual understanding, providing new insights and approaches to address agricultural pests and diseases. By open-sourcing our dataset and model, we aim to promote research and development in LMMs within the agricultural domain and make significant contributions to tackle the challenges of agricultural pests and diseases. All resources can be found at https://github.com/Kki2Eve/Agri-LLaVA.

Qingyong Hu, Bo Yang, Guangchi Fang et al.

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. The code is available at https://github.com/QingyongHu/SQN.

Grigorios Kalliatakis, Shoaib Ehsan, Ales Leonardis et al.

Identifying potential abuses of human rights through imagery is a novel and challenging task in the field of computer vision, that will enable to expose human rights violations over large-scale data that may otherwise be impossible. While standard databases for object and scene categorisation contain hundreds of different classes, the largest available dataset of human rights violations contains only 4 classes. Here, we introduce the `Human Rights Archive Database' (HRA), a verified-by-experts repository of 3050 human rights violations photographs, labelled with human rights semantic categories, comprising a list of the types of human rights abuses encountered at present. With the HRA dataset and a two-phase transfer learning scheme, we fine-tuned the state-of-the-art deep convolutional neural networks (CNNs) to provide human rights violations classification CNNs (HRA-CNNs). We also present extensive experiments refined to evaluate how well object-centric and scene-centric CNN features can be combined for the task of recognising human rights abuses. With this, we show that HRA database poses a challenge at a higher level for the well studied representation learning methods, and provide a benchmark in the task of human rights violations recognition in visual context. We expect this dataset can help to open up new horizons on creating systems able of recognising rich information about human rights violations. Our dataset, codes and trained models are available online at https://github.com/GKalliatakis/Human-Rights-Archive-CNNs.

Linfang Zheng, Tze Ho Elden Tse, Chen Wang et al.

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information. Additionally, we introduce a cross-cloud transformation mechanism that efficiently merges diverse data sources. Finally, we push the limits of our model by incorporating the shape prior information for translation and size error prediction. We conducted extensive experiments to demonstrate the effectiveness of the proposed framework. Through extensive quantitative experiments, we demonstrate significant improvement over the baseline method by a large margin across all metrics.

Yehe Liu, Alexander Krull, Hector Basevi et al.

Quanta image sensors, such as SPAD arrays, are an emerging sensor technology, producing 1-bit arrays representing photon detection events over exposures as short as a few nanoseconds. In practice, raw data are post-processed using heavy spatiotemporal binning to create more useful and interpretable images at the cost of degrading spatiotemporal resolution. In this work, we propose bit2bit, a new method for reconstructing high-quality image stacks at the original spatiotemporal resolution from sparse binary quanta image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data by predicting the photon arrival location probability distribution. However, due to the binary nature of the data, we show that the assumption of a Poisson distribution is inadequate. Instead, we model the process with a Bernoulli lattice process from the truncated Poisson. This leads to the proposal of a novel self-supervised solution based on a masked loss function. We evaluate our method using both simulated and real data. On simulated data from a conventional video, we achieve 34.35 mean PSNR with extremely photon-sparse binary input (<0.06 photons per pixel per frame). We also present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions. The scenes cover strong/weak ambient light, strong motion, ultra-fast events, etc., which will be made available to the community, on which we demonstrate the promise of our approach. Both reconstruction quality and throughput substantially surpass the state-of-the-art methods (e.g., Quanta Burst Photography (QBP)). Our approach significantly enhances the visualization and usability of the data, enabling the application of existing analysis techniques.

Tze Ho Elden Tse, Runyang Feng, Linfang Zheng et al.

With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise seen actions on unseen objects due to the limitations in representing object shape and movement using 3D bounding boxes. Additionally, the reliance on object templates at test time limits their generalisability to unseen objects. To address these challenges, we propose to leverage superquadrics as an alternative 3D object representation to bounding boxes and demonstrate their effectiveness on both template-free object reconstruction and action recognition tasks. Moreover, as we find that pure appearance-based methods can outperform the unified methods, the potential benefits from 3D geometric information remain unclear. Therefore, we study the compositionality of actions by considering a more challenging task where the training combinations of verbs and nouns do not overlap with the testing split. We extend H2O and FPHA datasets with compositional splits and design a novel collaborative learning framework that can explicitly reason about the geometric relations between hands and the manipulated object. Through extensive quantitative and qualitative evaluations, we demonstrate significant improvements over the state-of-the-arts in (compositional) action recognition.

Nora Horanyi, Kedi Xia, Kwang Moo Yi et al.

We propose a novel optimization framework that crops a given image based on user description and aesthetics. Unlike existing image cropping methods, where one typically trains a deep network to regress to crop parameters or cropping actions, we propose to directly optimize for the cropping parameters by repurposing pre-trained networks on image captioning and aesthetic tasks, without any fine-tuning, thereby avoiding training a separate network. Specifically, we search for the best crop parameters that minimize a combined loss of the initial objectives of these networks. To make the optimization table, we propose three strategies: (i) multi-scale bilinear sampling, (ii) annealing the scale of the crop region, therefore effectively reducing the parameter space, (iii) aggregation of multiple optimization results. Through various quantitative and qualitative evaluations, we show that our framework can produce crops that are well-aligned to intended user descriptions and aesthetically pleasing.

HyunJun Jung, Nikolas Brasch, Ales Leonardis et al.

Indirect Time-of-Flight (I-ToF) imaging is a widespread way of depth estimation for mobile devices due to its small size and affordable price. Previous works have mainly focused on quality improvement for I-ToF imaging especially curing the effect of Multi Path Interference (MPI). These investigations are typically done in specifically constrained scenarios at close distance, indoors and under little ambient light. Surprisingly little work has investigated I-ToF quality improvement in real-life scenarios where strong ambient light and far distances pose difficulties due to an extreme amount of induced shot noise and signal sparsity, caused by the attenuation with limited sensor power and light scattering. In this work, we propose a new learning based end-to-end depth prediction network which takes noisy raw I-ToF signals as well as an RGB image and fuses their latent representation based on a multi step approach involving both implicit and explicit alignment to predict a high quality long range depth map aligned to the RGB viewpoint. We test our approach on challenging real-world scenes and show more than 40% RMSE improvement on the final depth map compared to the baseline approach.

Song Yan, Jinyu Yang, Ales Leonardis et al.

Depth (D) indicates occlusion and is less sensitive to illumination changes, which make depth attractive modality for Visual Object Tracking (VOT). Depth is used in RGBD object tracking where the best trackers are deep RGB trackers with additional heuristic using depth maps. There are two potential reasons for the heuristics: 1) the lack of large RGBD tracking datasets to train deep RGBD trackers and 2) the long-term evaluation protocol of VOT RGBD that benefits from heuristics such as depth-based occlusion detection. In this work, we study how far D-only tracking can go if trained with large amounts of depth data. To compensate the lack of depth data, we generate depth maps for tracking. We train a "Depth-DiMP" from the scratch with the generated data and fine-tune it with the available small RGBD tracking datasets. The depth-only DiMP achieves good accuracy in depth-only tracking and combined with the original RGB DiMP the end-to-end trained RGBD-DiMP outperforms the recent VOT 2020 RGBD winners.

Tianhong Dai, Wei Li, Xilei Cao et al.

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.

Nanqing Dong, Matteo Maggioni, Yongxin Yang et al.

This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs. While supervised image reconstruction aims to minimize residual terms directly, RCL alternatively builds a connection between residuals and CL by defining a novel instance discrimination pretext task, using residuals as the discriminative feature. Our formulation mitigates the severe task misalignment between instance discrimination pretext tasks and downstream image reconstruction tasks, present in existing CL frameworks. Experimentally, we find that RCL can learn robust and transferable representations that improve the performance of various downstream tasks, such as denoising and super resolution, in comparison with recent self-supervised methods designed specifically for noisy inputs. Additionally, our unsupervised pre-training can significantly reduce annotation costs whilst maintaining performance competitive with fully-supervised image reconstruction.

Xi Jia, Alexander Thorley, Wei Chen et al.

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this whilst retaining the fast inference speed of deep learning, we propose VR-Net, a novel cascaded variational network for unsupervised deformable image registration. Using the variable splitting optimization scheme, we first convert the image registration problem, established in a generic variational framework, into two sub-problems, one with a point-wise, closed-form solution while the other one is a denoising problem. We then propose two neural layers (i.e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i.e. generalized denoising layer). Finally, we cascade the warping layer, intensity consistency layer, and generalized denoising layer to form the VR-Net. Extensive experiments on three (two 2D and one 3D) cardiac magnetic resonance imaging datasets show that VR-Net outperforms state-of-the-art deep learning methods on registration accuracy, while maintains the fast inference speed of deep learning and the data-efficiency of variational model.

Jinjin Gu, Haoming Cai, Chao Dong et al.

This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual image processing algorithms and the corresponding subjective scores. Thus they can be used to develop and evaluate IQA methods on GAN-based distortions. The challenge has 270 registered participants in total. In the final testing stage, 13 participating teams submitted their models and fact sheets. Almost all of them have achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.

Wei Chen, Xi Jia, Hyung Jin Chang et al.

In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image. Previous methods suffer from inefficient category-level pose feature extraction which leads to low accuracy and inference speed. To tackle this problem, we propose a fast shape-based network (FS-Net) with efficient category-level feature extraction for 6D pose estimation. First, we design an orientation aware autoencoder with 3D graph convolution for latent feature extraction. The learned latent feature is insensitive to point shift and object size thanks to the shift and scale-invariance properties of the 3D graph convolution. Then, to efficiently decode category-level rotation information from the latent feature, we propose a novel decoupled rotation mechanism that employs two decoders to complementarily access the rotation information. Meanwhile, we estimate translation and size by two residuals, which are the difference between the mean of object points and ground truth translation, and the difference between the mean size of the category and ground truth size, respectively. Finally, to increase the generalization ability of FS-Net, we propose an online box-cage based 3D deformation mechanism to augment the training data. Extensive experiments on two benchmark datasets show that the proposed method achieves state-of-the-art performance in both category- and instance-level 6D object pose estimation. Especially in category-level pose estimation, without extra synthetic data, our method outperforms existing methods by 6.3% on the NOCS-REAL dataset.

Thomas Tanay, Aivar Sootla, Matteo Maggioni et al.

Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution. In this work, we focus on their stability as dynamical systems and show that they tend to fail catastrophically at inference time on long video sequences. To address this issue, we (1) introduce a diagnostic tool which produces input sequences optimized to trigger instabilities and that can be interpreted as visualizations of temporal receptive fields, and (2) propose two approaches to enforce the stability of a model during training: constraining the spectral norm or constraining the stable rank of its convolutional layers. We then introduce Stable Rank Normalization for Convolutional layers (SRN-C), a new algorithm that enforces these constraints. Our experimental results suggest that SRN-C successfully enforces stability in recurrent video processing models without a significant performance loss.

Carlo Biffi, Steven McDonagh, Philip Torr et al.

Object detection has witnessed significant progress by relying on large, manually annotated datasets. Annotating such datasets is highly time consuming and expensive, which motivates the development of weakly supervised and few-shot object detection methods. However, these methods largely underperform with respect to their strongly supervised counterpart, as weak training signals \emph{often} result in partial or oversized detections. Towards solving this problem we introduce, for the first time, an online annotation module (OAM) that learns to generate a many-shot set of \emph{reliable} annotations from a larger volume of weakly labelled images. Our OAM can be jointly trained with any fully supervised two-stage object detection method, providing additional training annotations on the fly. This results in a fully end-to-end strategy that only requires a low-shot set of fully annotated images. The integration of the OAM with Fast(er) R-CNN improves their performance by $17\%$ mAP, $9\%$ AP50 on PASCAL VOC 2007 and MS-COCO benchmarks, and significantly outperforms competing methods using mixed supervision.

Lin Liu, Jianzhuang Liu, Shanxin Yuan et al.

When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoireing. Existing image restoration methods working in the RGB domain have difficulty in distinguishing moire patterns from true scene texture. Unlike these methods, our network removes moire patterns in the wavelet domain to separate the frequencies of moire patterns from the image content. The network combines dense convolution modules and dilated convolution modules supporting large receptive fields. Extensive experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moire artifacts on non-screen images. Although designed for image demoireing, WDNet has been applied to two other low-levelvision tasks, outperforming state-of-the-art image deraining and derain-drop methods on the Rain100h and Raindrop800 data sets, respectively.

Shanxin Yuan, Radu Timofte, Ales Leonardis et al.

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

Bolun Zheng, Shanxin Yuan, Gregory Slabaugh et al.

Image demoireing is a multi-faceted image restoration task involving both texture and color restoration. In this paper, we propose a novel multiscale bandpass convolutional neural network (MBCNN) to address this problem. As an end-to-end solution, MBCNN respectively solves the two sub-problems. For texture restoration, we propose a learnable bandpass filter (LBF) to learn the frequency prior for moire texture removal. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tuning of the color per pixel. Through an ablation study, we demonstrate the effectiveness of the different components of MBCNN. Experimental results on two public datasets show that our method outperforms state-of-the-art methods by a large margin (more than 2dB in terms of PSNR).

Matthias De Lange, Xu Jia, Sarah Parisot et al.

This work investigates the task of unsupervised model personalization, adapted to continually evolving, unlabeled local user images. We consider the practical scenario where a high capacity server interacts with a myriad of resource-limited edge devices, imposing strong requirements on scalability and local data privacy. We aim to address this challenge within the continual learning paradigm and provide a novel Dual User-Adaptation framework (DUA) to explore the problem. This framework flexibly disentangles user-adaptation into model personalization on the server and local data regularization on the user device, with desirable properties regarding scalability and privacy constraints. First, on the server, we introduce incremental learning of task-specific expert models, subsequently aggregated using a concealed unsupervised user prior. Aggregation avoids retraining, whereas the user prior conceals sensitive raw user data, and grants unsupervised adaptation. Second, local user-adaptation incorporates a domain adaptation point of view, adapting regularizing batch normalization parameters to the user data. We explore various empirical user configurations with different priors in categories and a tenfold of transforms for MIT Indoor Scene recognition, and classify numbers in a combined MNIST and SVHN setup. Extensive experiments yield promising results for data-driven local adaptation and elicit user priors for server adaptation to depend on the model rather than user data. Hence, although user-adaptation remains a challenging open problem, the DUA framework formalizes a principled foundation for personalizing both on server and user device, while maintaining privacy and scalability.

Wei Chen, Xi Jia, Hyung Jin Chang et al.

In this paper, we propose a novel real-time 6D object pose estimation framework, named G2L-Net. Our network operates on point clouds from RGB-D detection in a divide-and-conquer fashion. Specifically, our network consists of three steps. First, we extract the coarse object point cloud from the RGB-D image by 2D detection. Second, we feed the coarse object point cloud to a translation localization network to perform 3D segmentation and object translation prediction. Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation. In the third step, we define point-wise embedding vector features to capture viewpoint-aware information. To calculate more accurate rotation, we adopt a rotation residual estimator to estimate the residual between initial rotation and ground truth, which can boost initial pose estimation performance. Our proposed G2L-Net is real-time despite the fact multiple steps are stacked via the proposed coarse-to-fine framework. Extensive experiments on two benchmark datasets show that G2L-Net achieves state-of-the-art performance in terms of both accuracy and speed.

Daniel Hernandez-Juarez, Sarah Parisot, Benjamin Busam et al.

Contemporary approaches frame the color constancy problem as learning camera specific illuminant mappings. While high accuracy can be achieved on camera specific data, these models depend on camera spectral sensitivity and typically exhibit poor generalisation to new devices. Additionally, regression methods produce point estimates that do not explicitly account for potential ambiguities among plausible illuminant solutions, due to the ill-posed nature of the problem. We propose a Bayesian framework that naturally handles color constancy ambiguity via a multi-hypothesis strategy. Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images. Secondly, we estimate, for each corrected image, the likelihood of the light source being achromatic using a camera-agnostic CNN. Finally, our method explicitly learns a final illumination estimate from the generated posterior probability distribution. Our likelihood estimator learns to answer a camera-agnostic question and thus enables effective multi-camera training by disentangling illuminant estimation from the supervised learning task. We extensively evaluate our proposed approach and additionally set a benchmark for novel sensor generalisation without re-training. Our method provides state-of-the-art accuracy on multiple public datasets (up to 11% median angular error improvement) while maintaining real-time execution.

Shanxin Yuan, Radu Timofte, Gregory Slabaugh et al.

This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. This paper describes the challenge, and focuses on the proposed solutions and their results. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. A new dataset, called LCDMoire was created for this challenge, and consists of 10,200 synthetically generated image pairs (moire and clean ground truth). The challenge was divided into 2 tracks. Track 1 targeted fidelity, measuring the ability of demoire methods to obtain a moire-free image compared with the ground truth, while Track 2 examined the perceptual quality of demoire methods. The tracks had 60 and 39 registered participants, respectively. A total of eight teams competed in the final testing phase. The entries span the current the state-of-the-art in the image demoireing problem.

Shanxin Yuan, Radu Timofte, Gregory Slabaugh et al.

This paper introduces a novel dataset, called LCDMoire, which was created for the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. The dataset comprises 10,200 synthetically generated image pairs (consisting of an image degraded by moire and a clean ground truth image). In addition to describing the dataset and its creation, this paper also reviews the challenge tracks, competition, and results, the latter summarizing the current state-of-the-art on this dataset.

Matthias De Lange, Rahaf Aljundi, Marc Masana et al.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.

Umit Rusen Aktas, Chao Zhao, Marek Kopicki et al.

Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second we present a data set, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we present a basic architecture for generation and evaluation of dexterous grasps that may be trained in a supervised manner. Fourth, we present three different evaluative architectures, employing ResNet-50 or VGG16 as their visual backbone. Fifth, we train, and evaluate seventeen variants of generative-evaluative architectures on this simulated data set, showing improvement from 69.53% grasp success rate to 90.49%. Finally, we present a real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8% on real novel objects seen from a single view, improving on a baseline of 57.1%.

Steven McDonagh, Sarah Parisot, Fengwei Zhou et al.

Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit state-of-the-art estimation accuracy with camera-specific labelled training imagery. Resulting models typically suffer from domain gaps and fail to generalise across imaging devices. In this work, we propose a new approach that affords fast adaptation to previously unseen cameras, and robustness to changes in capture device by leveraging annotated samples across different cameras and datasets. We present a general approach that utilizes the concept of color temperature to frame color constancy as a set of distinct, homogeneous few-shot regression tasks, each associated with an intuitive physical meaning. We integrate this novel formulation within a meta-learning framework, enabling fast generalisation to previously unseen cameras using only handfuls of camera specific training samples. Consequently, the time spent for data collection and annotation substantially diminishes in practice whenever a new sensor is used. To quantify this gain, we evaluate our pipeline on three publicly available datasets comprising 12 different cameras and diverse scene content. Our approach delivers competitive results both qualitatively and quantitatively while requiring a small fraction of the camera-specific samples compared to standard approaches.

Tomas Hodan, Rigas Kouskouridas, Tae-Kyun Kim et al.

This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and an introduction of the BOP benchmark for 6D object pose estimation. The workshop was attended by 100+ people working on relevant topics in both academia and industry who shared up-to-date advances and discussed open problems.

Grigorios Kalliatakis, Anca Sticlaru, George Stamatiadis et al.

We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03% mean average precision when classifying materials in cross-dataset scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from ~ 5% to ~ 19% across three widely used material databases of real-world images.

Bruno Ferrarini, Shoaib Ehsan, Ales Leonardis et al.

Selecting the most suitable local invariant feature detector for a particular application has rendered the task of evaluating feature detectors a critical issue in vision research. Although the literature offers a variety of comparison works focusing on performance evaluation of image feature detectors under several types of image transformations, the influence of the scene content on the performance of local feature detectors has received little attention so far. This paper aims to bridge this gap with a new framework for determining the type of scenes which maximize and minimize the performance of detectors in terms of repeatability rate. The results are presented for several state-of-the-art feature detectors that have been obtained using a large image database of 20482 images under JPEG compression, uniform light and blur changes with 539 different scenes captured from real-world scenarios. These results provide new insights into the behavior of feature detectors.

Grigorios Kalliatakis, Shoaib Ehsan, Maria Fasli et al.

After setting the performance benchmarks for image, video, speech and audio processing, deep convolutional networks have been core to the greatest advances in image recognition tasks in recent times. This raises the question of whether there are any benefit in targeting these remarkable deep architectures with the unattempted task of recognising human rights violations through digital images. Under this perspective, we introduce a new, well-sampled human rights-centric dataset called Human Rights Understanding (HRUN). We conduct a rigorous evaluation on a common ground by combining this dataset with different state-of-the-art deep convolutional architectures in order to achieve recognition of human rights violations. Experimental results on the HRUN dataset have shown that the best performing CNN architectures can achieve up to 88.10\% mean average precision. Additionally, our experiments demonstrate that increasing the size of the training samples is crucial for achieving an improvement on mean average precision principally when utilising very deep networks.

Grigorios Kalliatakis, Georgios Stamatiadis, Shoaib Ehsan et al.

Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising Convolutional Neural Networks (CNNs), we empirically study material classification of everyday objects employing these techniques. More specifically, we conduct a rigorous evaluation of how state-of-the art CNN architectures compare on a common ground over widely used material databases. Experimental results on three challenging material databases show that the best performing CNN architectures can achieve up to 94.99\% mean average precision when classifying materials.

Jingjing Xiao, Qiang Lan, Linbo Qiao et al.

This article presents a semantic tracker which simultaneously tracks a single target and recognises its category. In general, it is hard to design a tracking model suitable for all object categories, e.g., a rigid tracker for a car is not suitable for a deformable gymnast. Category-based trackers usually achieve superior tracking performance for the objects of that specific category, but have difficulties being generalised. Therefore, we propose a novel unified robust tracking framework which explicitly encodes both generic features and category-based features. The tracker consists of a shared convolutional network (NetS), which feeds into two parallel networks, NetC for classification and NetT for tracking. NetS is pre-trained on ImageNet to serve as a generic feature extractor across the different object categories for NetC and NetT. NetC utilises those features within fully connected layers to classify the object category. NetT has multiple branches, corresponding to multiple categories, to distinguish the tracked object from the background. Since each branch in NetT is trained by the videos of a specific category or groups of similar categories, NetT encodes category-based features for tracking. During online tracking, NetC and NetT jointly determine the target regions with the right category and foreground labels for target estimation. To improve the robustness and precision, NetC and NetT inter-supervise each other and trigger network adaptation when their outputs are ambiguous for the same image regions (i.e., when the category label contradicts the foreground/background classification). We have compared the performance of our tracker to other state-of-the-art trackers on a large-scale tracking benchmark (100 sequences)---the obtained results demonstrate the effectiveness of our proposed tracker as it outperformed other 38 state-of-the-art tracking algorithms.

Bruno Ferrarini, Shoaib Ehsan, Naveed Ur Rehman et al.

A large number of different feature detectors has been proposed so far. Any existing approach presents strengths and weaknesses, which make a detector optimal only for a limited range of applications. A tool capable of selecting the optimal feature detector in relation to the operating conditions is presented in this paper. The input images are quickly analyzed to determine what type of image transformation is applied to them and at which amount. Finally, the detector that is expected to obtain the highest repeatability under such conditions, is chosen to extract features from the input images. The efficiency and the good accuracy in determining the optimal feature detector for any operating condition, make the proposed tool suitable to be utilized in real visual applications. %A large number of different feature detectors has been proposed so far. Any existing approach presents strengths and weaknesses, which make a detector optimal only for a limited range of applications. A large number of different local feature detectors have been proposed in the last few years. However, each feature detector has its own strengths ad weaknesses that limit its use to a specific range of applications. In this paper is presented a tool capable of quickly analysing input images to determine which type and amount of transformation is applied to them and then selecting the optimal feature detector, which is expected to perform the best. The results show that the performance and the fast execution time render the proposed tool suitable for real-world vision applications.

Shoaib Ehsan, Adrian F. Clark, Ales Leonardis et al.

Since local feature detection has been one of the most active research areas in computer vision during the last decade, a large number of detectors have been proposed. The interest in feature-based applications continues to grow and has thus rendered the task of characterizing the performance of various feature detection methods an important issue in vision research. Inspired by the good practices of electronic system design, a generic framework based on the repeatability measure is presented in this paper that allows assessment of the upper and lower bounds of detector performance and finds statistically significant performance differences between detectors as a function of image transformation amount by introducing a new variant of McNemars test in an effort to design more reliable and effective vision systems. The proposed framework is then employed to establish operating and guarantee regions for several state-of-the-art detectors and to identify their statistical performance differences for three specific image transformations: JPEG compression, uniform light changes and blurring. The results are obtained using a newly acquired, large image database (20482) images with 539 different scenes. These results provide new insights into the behaviour of detectors and are also useful from the vision systems design perspective.