Analyzing and understanding hand information from multimedia materials like images or videos is important for many real world applications and remains to be very active in research community. There are various works focusing on recovering hand information from single image, however, they usually solve a single task, for example, hand mask segmentation, 2D/3D hand pose estimation, or hand mesh reconstruction and perform not well in challenging scenarios. To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework (HIU-DMTL) to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks. To achieve this goal, a cascaded multi-task learning (MTL) backbone is designed to estimate the 2D heat maps, to learn the segmentation mask, and to generate the intermediate 3D information encoding, followed by a coarse-to-fine learning paradigm and a self-supervised learning strategy. Qualitative experiments demonstrate that our approach is capable of recovering reasonable mesh representations even in challenging situations. Quantitatively, our method significantly outperforms the state-of-the-art approaches on various widely-used datasets, in terms of diverse evaluation metrics.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
Recovering dense human poses from images plays a critical role in establishing an image-to-surface correspondence between RGB images and the 3D surface of the human body, serving the foundation of rich real-world applications, such as virtual humans, monocular-to-3d reconstruction. However, the popular DensePose-COCO dataset relies on a sophisticated manual annotation system, leading to severe limitations in acquiring the denser and more accurate annotated pose resources. In this work, we introduce a new 3D human-body model with a series of decoupled parameters that could freely control the generation of the body. Furthermore, we build a data generation system based on this decoupling 3D model, and construct an ultra dense synthetic benchmark UltraPose, containing around 1.3 billion corresponding points. Compared to the existing manually annotated DensePose-COCO dataset, the synthetic UltraPose has ultra dense image-to-surface correspondences without annotation cost and error. Our proposed UltraPose provides the largest benchmark and data resources for lifting the model capability in predicting more accurate dense poses. To promote future researches in this field, we also propose a transformer-based method to model the dense correspondence between 2D and 3D worlds. The proposed model trained on synthetic UltraPose can be applied to real-world scenarios, indicating the effectiveness of our benchmark and model.
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of vision transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current sate of the art with less floating-point operations and parameters. Our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a multi-task environment for dense prediction tasks, represented by a common backbone and independent task-specific heads. Our goal is to find the most efficient way to refine each task prediction by capturing cross-task contexts dependent on tasks' relations. We explore various attention-based contexts, such as global and local, in the multi-task setting and analyze their behavior when applied to refine each task independently. Empirical findings confirm that different source-target task pairs benefit from different context types. To automate the selection process, we propose an Adaptive Task-Relational Context (ATRC) module, which samples the pool of all available contexts for each task pair using neural architecture search and outputs the optimal configuration for deployment. Our method achieves state-of-the-art performance on two important multi-task benchmarks, namely NYUD-v2 and PASCAL-Context. The proposed ATRC has a low computational toll and can be used as a drop-in refinement module for any supervised multi-task architecture.
This paper proposes GraviCap, i.e., a new approach for joint markerless 3D human motion capture and object trajectory estimation from monocular RGB videos. We focus on scenes with objects partially observed during a free flight. In contrast to existing monocular methods, we can recover scale, object trajectories as well as human bone lengths in meters and the ground plane's orientation, thanks to the awareness of the gravity constraining object motions. Our objective function is parametrised by the object's initial velocity and position, gravity direction and focal length, and jointly optimised for one or several free flight episodes. The proposed human-object interaction constraints ensure geometric consistency of the 3D reconstructions and improved physical plausibility of human poses compared to the unconstrained case. We evaluate GraviCap on a new dataset with ground-truth annotations for persons and different objects undergoing free flights. In the experiments, our approach achieves state-of-the-art accuracy in 3D human motion capture on various metrics. We urge the reader to watch our supplementary video. Both the source code and the dataset are released; see http://4dqv.mpi-inf.mpg.de/GraviCap/.
In dynamic neural networks that adapt computations to different inputs, gating-based methods have demonstrated notable generality and applicability in trading-off the model complexity and accuracy. However, existing works only explore the redundancy from a single point of the network, limiting the performance. In this paper, we propose dual gating, a new dynamic computing method, to reduce the model complexity at run-time. For each convolutional block, dual gating identifies the informative features along two separate dimensions, spatial and channel. Specifically, the spatial gating module estimates which areas are essential, and the channel gating module predicts the salient channels that contribute more to the results. Then the computation of both unimportant regions and irrelevant channels can be skipped dynamically during inference. Extensive experiments on a variety of datasets demonstrate that our method can achieve higher accuracy under similar computing budgets compared with other dynamic execution methods. In particular, dynamic dual gating can provide 59.7% saving in computing of ResNet50 with 76.41% top-1 accuracy on ImageNet, which has advanced the state-of-the-art.
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion in the datasets, but tend to have the lowest performance. In this paper, we confront the challenge of short actions and propose a multi-level cross-scale solution dubbed as video self-stitching graph network (VSGN). We have two key components in VSGN: video self-stitching (VSS) and cross-scale graph pyramid network (xGPN). In VSS, we focus on a short period of a video and magnify it along the temporal dimension to obtain a larger scale. We stitch the original clip and its magnified counterpart in one input sequence to take advantage of the complementary properties of both scales. The xGPN component further exploits the cross-scale correlations by a pyramid of cross-scale graph networks, each containing a hybrid module to aggregate features from across scales as well as within the same scale. Our VSGN not only enhances the feature representations, but also generates more positive anchors for short actions and more short training samples. Experiments demonstrate that VSGN obviously improves the localization performance of short actions as well as achieving the state-of-the-art overall performance on THUMOS-14 and ActivityNet-v1.3.
Although text recognition has significantly evolved over the years, state-of the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artifacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder that performs joint visual-semantic reasoning. Our novelty lies in the intuition that for text recognition, prediction should be refined in a stage-wise manner. Therefore our key contribution is in designing a stage-wise unrolling attentional decoder where non-differentiability, invoked by discretely predicted character labels, needs to be bypassed for end-to-end training. While the first stage predicts using visual features, subsequent stages refine on-top of it using joint visual-semantic information. Additionally, we introduce multi-scale 2D attention along with dense and residual connections between different stages to deal with varying scales of character sizes, for better performance and faster convergence during training. Experimental results show our approach to outperform existing SOTA methods by a considerable margin.
TravelNet: Self-Supervised Physically Plausible Hand Motion Learning From Monocular Color Images
PDF ↗This paper aims to reconstruct physically plausible hand motion from monocular color images. Existing frame-by-frame estimating approaches can not guarantee the physical plausibility (e.g. penetration, jittering) directly. In this paper, we embed physical constraints on the per-frame estimated motions in both spatial and temporal space. Our key idea is to adopt a self-supervised learning strategy to train a novel encoder-decoder, named TravelNet, whose training motion data is prepared by the physics engine using discrete pose states. TravelNet captures key pose states from hand motion sequences as compact motion descriptors, inspired by the concept of keyframes in animation. Finally, it manages to extract those key states out of perturbations without manual annotations, and reconstruct the motions preserving details and physical plausibility. In the experiments, we show that the outputs of the TravelNet contain both finger synergism and time consistency. Through the proposed framework, hand motions can be accurately reconstructed and flexibly re-edited, which is superior to the state-of-the-art methods.
We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing of individual heads are then combined together resulting in the update of point features. Using the new block, we build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks. The resulting architectures achieve state-of-the-art performance for these tasks, demonstrating the versatility of the new block for point cloud processing.
With the thriving of deep learning, CNN-based object detectors have made great progress in the past decade. However, the domain gap between training and testing data leads to a prominent performance degradation and thus hinders their application in the real world. To alleviate this problem, Knowledge Transfer Network (KTNet) is proposed as a new paradigm for domain adaption. Specifically, KTNet is constructed on a base detector with intrinsic knowledge mining and relational knowledge constraints. First, we design a foreground/background classifier shared by source domain and target domain to extract the common attribute knowledge of objects in different scenarios. Second, we model the relational knowledge graph and explicitly constrain the consistency of category correlation under source domain, target domain, as well as cross-domain conditions. As a result, the detector is guided to learn object-related and domain-independent representation. Extensive experiments and visualizations confirm that transferring object-specific knowledge can yield notable performance gains. The proposed KTNet achieves state-of-the-art results on three cross-domain detection benchmarks.
Recent progress in multi-object tracking (MOT) has shown great significance of a robust scoring mechanism for potential tracks. However, the lack of available data in MOT makes it difficult to learn a general scoring mechanism. Multiple cues including appearance, motion and etc., are limitedly utilized in current manual scoring functions. In this paper, we propose a Multiple Nodes Tracking (MNT) framework that adapts to most trackers. Based on this framework, a Recurrent Tracking Unit (RTU) is designed to score potential tracks through long-term information. In addition, we present a method of generating simulated tracking data without real data to overcome the defect of limited available data in MOT. The experiments demonstrate that our simulated tracking data is effective for training RTU and achieves state-of-the-art performance on both MOT17 and MOT16 benchmarks. Meanwhile, RTU can be flexibly plugged into classic trackers such as DeepSORT and MHT, and makes remarkable improvements as well.
This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report state-of-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff.
Unsupervised domain adaptation for semantic segmentation aims to assign the pixel-level labels for unlabeled target domain by transferring knowledge from the labeled source domain. A typical self-supervised learning approach generates pseudo labels from the source model and then re-trains the model to fit the target distribution. However, it suffers from noisy pseudo labels due to the existence of domain shift. Related works alleviate this problem by selecting high-confidence predictions, but uncertain classes with low confidence scores have rarely been considered. This informative uncertainty is essential to enhance feature representation and align source and target domains. In this paper, we propose a novel uncertainty-aware pseudo label refinery framework considering two crucial factors simultaneously. First, we progressively enhance the feature alignment model via the target-guided uncertainty rectifying framework. Second, we provide an uncertainty-aware pseudo label assignment strategy without any manually designed threshold to reduce the noisy labels. Extensive experiments demonstrate the effectiveness of our proposed approach and achieve state-of-the-art performance on two standard synthetic-2-real tasks.
Recent work has shown impressive results on data-driven defocus deblurring using the two-image views available on modern dual-pixel (DP) sensors. One significant challenge in this line of research is access to DP data. Despite many cameras having DP sensors, only a limited number provide access to the low-level DP sensor images. In addition, capturing training data for defocus deblurring involves a time-consuming and tedious setup requiring the camera's aperture to be adjusted. Some cameras with DP sensors (e.g., smartphones) do not have adjustable apertures, further limiting the ability to produce the necessary training data. We address the data capture bottleneck by proposing a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a recurrent convolutional network (RCN) architecture that improves deblurring results and is suitable for use with single-frame and multi-frame data (e.g., video) captured by DP sensors. Finally, we show that our synthetic DP data is useful for training DNN models targeting video deblurring applications where access to DP data remains challenging.
Real-world machine learning systems need to analyze novel testing data that differs from the training data. In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes. Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised learning the closed-set data distribution with a GAN and using its discriminator as the open-set likelihood function. However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which unlikely exhaustively span the open-world. The latter does not work well, presumably due to the instable training of GANs. Motivated by the above, we propose OpenGAN, which addresses the limitation of each approach by combining them with several technical insights. First, we show that a carefully selected GAN-discriminator on some real outlier data already achieves the state-of-the-art. Second, we augment the available set of real open training examples with adversarially synthesized ""fake"" data. Third and most importantly, we build the discriminator over the features computed by the closed-world K-way networks. Extensive experiments show that OpenGAN significantly outperforms prior open-set methods.
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce neural blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the learned blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. Experiments show that our approach significantly outperforms recent human synthesis methods. The code and supplementary materials are available at \href https://zju3dv.github.io/animatable_nerf/ https://zju3dv.github.io/animatable_nerf/ .
We learn an interactive vision-based driving policy from pre-recorded driving logs via a model-based approach. A forward model of the world supervises a driving policy that predicts the outcome of any potential driving trajectory. To support learning from pre-recorded logs, we assume that the world is on rails, meaning neither the agent nor its actions influence the environment. This assumption greatly simplifies the learning problem, factorizing the dynamics into a nonreactive world model and a low-dimensional and compact forward model of the ego-vehicle. Our approach computes action-values for each training trajectory using a tabular dynamic-programming evaluation of the Bellman equations; these action-values in turn supervise the final vision-based driving policy. Despite the world-on-rails assumption, the final driving policy acts well in a dynamic and reactive world. It outperforms imitation learning as well as model-based and model-free reinforcement learning on the challenging CARLA NoCrash benchmark. It is also an order of magnitude more sample-efficient than state-of-the-art model-free reinforcement learning techniques on navigational tasks in the ProcGen benchmark.
DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling
PDF ↗Since 2014 transfer learning has become the key driver for the improvement of spatial saliency prediction - however, with stagnant progress in the last 3-5 years. We conduct a large-scale transfer learning study which tests different ImageNet backbones, always using the same read out architecture and learning protocol adopted from DeepGaze II. By replacing the VGG19 backbone of DeepGaze II with ResNet50 features we improve the performance on saliency prediction from 78% to 85%. However, as we continue to test better ImageNet models as backbones - such as EfficientNetB5 - we observe no additional improvement on saliency prediction. By analyzing the backbones further, we find that generalization to other datasets differs substantially, with models being consistently overconfident in their fixation predictions. We show that by combining multiple backbones in a principled manner a good confidence calibration on unseen datasets can be achieved. This new model "DeepGaze IIE" yields a significant leap in benchmark performance in and out-of-domain with a 15 percent point improvement over DeepGaze II to 93% on MIT1003, marking a new state of the art on the MIT/Tuebingen Saliency Benchmark in all available metrics (AUC: 88.3%, sAUC: 79.4%, CC: 82.4%).
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of the scene. However, indoor scenes contain complex 3D light transport where a 2D representation is insufficient. In this paper, we propose a unified, learning-based inverse rendering framework that formulates 3D spatially-varying lighting. Inspired by classic volume rendering techniques, we propose a novel Volumetric Spherical Gaussian representation for lighting, which parameterizes the exitant radiance of the 3D scene surfaces on a voxel grid. We design a physicsbased differentiable renderer that utilizes our 3D lighting representation, and formulates the energy-conserving image formation process that enables joint training of all intrinsic properties with the re-rendering constraint. Our model ensures physically correct predictions and avoids the need for ground-truth HDR lighting which is not easily accessible. Experiments show that our method outperforms prior works both quantitatively and qualitatively, and is capable of producing photorealistic results for AR applications such as virtual object insertion even for highly specular objects.