Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require streaming 3D assets to facilitate client-side interactions such as object manipulation and viewpoint movement. Compared to audio and video streaming, 3D streaming often requires larger data sizes and yet lower latency to ensure sufficient rendering quality, resolution, and latency for perceptual comfort. Thus, streaming 3D assets can be even more challenging than streaming audios/videos, and existing solutions often suffer from long loading time or limited quality. To address this critical and timely issue, we propose a perceptually-optimized progressive 3D streaming method for spatial quality and temporal consistency in immersive interactions. Based on the human visual mechanisms in the frequency domain, our model selects and schedules the streaming dataset for optimal spatial-temporal quality. We also train a neural network for our model to accelerate this decision process for real-time client-server applications. We evaluate our method via subjective studies and objective analysis under varying network conditions (from 3G to 5G) and client devices (HMD and traditional displays), and demonstrate better visual quality and temporal consistency than alternative solutions.
相關內容
Appearance-based gaze estimation aims to predict the 3D eye gaze direction from a single image. While recent deep learning-based approaches have demonstrated excellent performance, they usually assume one calibrated face in each input image and cannot output multi-person gaze in real time. However, simultaneous gaze estimation for multiple people in the wild is necessary for real-world applications. In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image. In addition, we design a sophisticated data generation pipeline and propose a new dataset, MPSGaze, which contains full images of multiple people with 3D gaze ground truth. Experimental results demonstrate that our unified framework not only offers a faster speed, but also provides a lower gaze estimation error compared with state-of-the-art methods. This technique can be useful in real-time applications with multiple users.
Computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.
The majority of internet traffic is video content. This drives the demand for video compression to deliver high quality video at low target bitrates. Optimising the parameters of a video codec for a specific video clip (per-clip optimisation) has been shown to yield significant bitrate savings. In previous work we have shown that per-clip optimisation of the Lagrangian multiplier leads to up to 24% BD-Rate improvement. A key component of these algorithms is modeling the R-D characteristic across the appropriate bitrate range. This is computationally heavy as it usually involves repeated video encodes of the high resolution material at different parameter settings. This work focuses on reducing this computational load by deploying a NN operating on lower bandwidth features. Our system achieves BD-Rate improvement in approximately 90% of a large corpus with comparable results to previous work in direct optimisation.
The majority of internet traffic is video content. This drives the demand for video compression in order to deliver high quality video at low target bitrates. This paper investigates the impact of adjusting the rate distortion equation on compression performance. An constant of proportionality, k, is used to modify the Lagrange multiplier used in H.265 (HEVC). Direct optimisation methods are deployed to maximise BD-Rate improvement for a particular clip. This leads to up to 21% BD-Rate improvement for an individual clip. Furthermore we use a more realistic corpus of material provided by YouTube. The results show that direct optimisation using BD-rate as the objective function can lead to further gains in bitrate savings that are not available with previous approaches.
We present PHORHUM, a novel, end-to-end trainable, deep neural network methodology for photorealistic 3D human reconstruction given just a monocular RGB image. Our pixel-aligned method estimates detailed 3D geometry and, for the first time, the unshaded surface color together with the scene illumination. Observing that 3D supervision alone is not sufficient for high fidelity color reconstruction, we introduce patch-based rendering losses that enable reliable color reconstruction on visible parts of the human, and detailed and plausible color estimation for the non-visible parts. Moreover, our method specifically addresses methodological and practical limitations of prior work in terms of representing geometry, albedo, and illumination effects, in an end-to-end model where factors can be effectively disentangled. In extensive experiments, we demonstrate the versatility and robustness of our approach. Our state-of-the-art results validate the method qualitatively and for different metrics, for both geometric and color reconstruction.
We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects. Though photorealistic images of articulated objects can be rendered with explicit pose control through existing 3D neural representations, these methods require ground truth 3D pose and foreground masks for training, which are expensive to obtain. We obviate this need by learning the representations with GAN training. From random poses and latent vectors, the generator is trained to produce realistic images of articulated objects by adversarial training. To avoid a large computational cost for GAN training, we propose an efficient neural representation for articulated objects based on tri-planes and then present a GAN-based framework for its unsupervised training. Experiments demonstrate the efficiency of our method and show that GAN-based training enables learning of controllable 3D representations without supervision.
In this paper, we consider the challenging task of simultaneously locating and recovering multiple hands from single 2D image. Previous studies either focus on single hand reconstruction or solve this problem in a multi-stage way. Moreover, the conventional two-stage pipeline firstly detects hand areas, and then estimates 3D hand pose from each cropped patch. To reduce the computational redundancy in preprocessing and feature extraction, we propose a concise but efficient single-stage pipeline. Specifically, we design a multi-head auto-encoder structure for multi-hand reconstruction, where each head network shares the same feature map and outputs the hand center, pose and texture, respectively. Besides, we adopt a weakly-supervised scheme to alleviate the burden of expensive 3D real-world data annotations. To this end, we propose a series of losses optimized by a stage-wise training scheme, where a multi-hand dataset with 2D annotations is generated based on the publicly available single hand datasets. In order to further improve the accuracy of the weakly supervised model, we adopt several feature consistency constraints in both single and multiple hand settings. Specifically, the keypoints of each hand estimated from local features should be consistent with the re-projected points predicted from global features. Extensive experiments on public benchmarks including FreiHAND, HO3D, InterHand2.6M and RHD demonstrate that our method outperforms the state-of-the-art model-based methods in both weakly-supervised and fully-supervised manners.
This paper presents a hybrid robot motion planner that generates long-horizon motion plans for robot navigation in environments with obstacles. We propose a hybrid planner, RRT* with segmented trajectory optimization (RRT*-sOpt), which combines the merits of sampling-based planning, optimization-based planning, and trajectory splitting to quickly plan for a collision-free and dynamically-feasible motion plan. When generating a plan, the RRT* layer quickly samples a semi-optimal path and sets it as an initial reference path. Then, the sOpt layer splits the reference path and performs optimization on each segment. It then splits the new trajectory again and repeats the process until the whole trajectory converges. We also propose to reduce the number of segments before convergence with the aim of further reducing computation time. Simulation results show that RRT*-sOpt benefits from the hybrid structure with trajectory splitting and performs robustly in various robot platforms and scenarios.
Deep learning approaches have demonstrated success in modeling analog audio effects. Nevertheless, challenges remain in modeling more complex effects that involve time-varying nonlinear elements, such as dynamic range compressors. Existing neural network approaches for modeling compression either ignore the device parameters, do not attain sufficient accuracy, or otherwise require large noncausal models prohibiting real-time operation. In this work, we propose a modification to temporal convolutional networks (TCNs) enabling greater efficiency without sacrificing performance. By utilizing very sparse convolutional kernels through rapidly growing dilations, our model attains a significant receptive field using fewer layers, reducing computation. Through a detailed evaluation we demonstrate our efficient and causal approach achieves state-of-the-art performance in modeling the analog LA-2A, is capable of real-time operation on CPU, and only requires 10 minutes of training data.
Obtaining a dynamic population distribution is key to many decision-making processes such as urban planning, disaster management and most importantly helping the government to better allocate socio-technical supply. For the aspiration of these objectives, good population data is essential. The traditional method of collecting population data through the census is expensive and tedious. In recent years, machine learning methods have been developed to estimate the population distribution. Most of the methods use data sets that are either developed on a small scale or not publicly available yet. Thus, the development and evaluation of the new methods become challenging. We fill this gap by providing a comprehensive data set for population estimation in 98 European cities. The data set comprises digital elevation model, local climate zone, land use classifications, nighttime lights in combination with multi-spectral Sentinel-2 imagery, and data from the Open Street Map initiative. We anticipate that it would be a valuable addition to the research community for the development of sophisticated machine learning-based approaches in the field of population estimation.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191