In the wake of many new ML-inspired approaches for reconstructing and representing high-quality 3D content, recent hybrid and explicitly learned representations exhibit promising performance and quality characteristics. However, their scaling to higher dimensions is challenging, e.g. when accounting for dynamic content with respect to additional parameters such as material properties, illumination, or time. In this paper, we tackle these challenges for an explicit representations based on Gaussian mixture models. With our solutions, we arrive at efficient fitting of compact N-dimensional Gaussian mixtures and enable efficient evaluation at render time: For fast fitting and evaluation, we introduce a high-dimensional culling scheme that efficiently bounds N-D Gaussians, inspired by Locality Sensitive Hashing. For adaptive refinement yet compact representation, we introduce a loss-adaptive density control scheme that incrementally guides the use of additional capacity towards missing details. With these tools we can for the first time represent complex appearance that depends on many input dimensions beyond position or viewing angle within a compact, explicit representation optimized in minutes and rendered in milliseconds.
相關內容
In the field of digital content creation, generating high-quality 3D characters from single images is challenging, especially given the complexities of various body poses and the issues of self-occlusion and pose ambiguity. In this paper, we present CharacterGen, a framework developed to efficiently generate 3D characters. CharacterGen introduces a streamlined generation pipeline along with an image-conditioned multi-view diffusion model. This model effectively calibrates input poses to a canonical form while retaining key attributes of the input image, thereby addressing the challenges posed by diverse poses. A transformer-based, generalizable sparse-view reconstruction model is the other core component of our approach, facilitating the creation of detailed 3D models from multi-view images. We also adopt a texture-back-projection strategy to produce high-quality texture maps. Additionally, we have curated a dataset of anime characters, rendered in multiple poses and views, to train and evaluate our model. Our approach has been thoroughly evaluated through quantitative and qualitative experiments, showing its proficiency in generating 3D characters with high-quality shapes and textures, ready for downstream applications such as rigging and animation.
This technical report describes the implementation of Toychain: a simple, lightweight blockchain implemented in Python, designed for ease of deployment and practicality in robotics research. It can be integrated with various software and simulation tools used in robotics (we have integrated it with ARGoS, Gazebo, and ROS2), and also be deployed on real robots capable of Wi-Fi communications. The Toychain package supports the deployment of smart contracts written in Python (computer programs that can be executed by and synchronized across a distributed network). The nodes in the blockchain can execute smart contract functions by broadcasting transactions, which update the state of the blockchain upon agreement by all other nodes. The conditions for this agreement are established by a consensus protocol. The Toychain package allows for custom implementations of the consensus protocol, which can be useful for research or meeting specific application requirements. Currently, Proof-of-Work and Proof-of-Authority are implemented.
Trajectory planners of autonomous vehicles usually rely on physical models to predict the vehicle behavior. However, despite their suitability, physical models have some shortcomings. On the one hand, simple models suffer from larger model errors and more restrictive assumptions. On the other hand, complex models are computationally more demanding and depend on environmental and operational parameters. In each case, the drawbacks can be associated to a certain degree to the physical modeling of the yaw rate dynamics. Therefore, this paper investigates the yaw rate prediction based on conditional neural processes (CNP), a data-driven meta-learning approach, to simultaneously achieve low errors, adequate complexity and robustness to varying parameters. Thus, physical models can be enhanced in a targeted manner to provide accurate and computationally efficient predictions to enable safe planning in autonomous vehicles. High fidelity simulations for a variety of driving scenarios and different types of cars show that CNP makes it possible to employ and transfer knowledge about the yaw rate based on current driving dynamics in a human-like manner, yielding robustness against changing environmental and operational conditions.
We evaluate the use of software interpretation to push High Level Synthesis of application-specific accelerators toward a higher level of abstraction. Our methodology is supported by a formal power consumption model that computes the power consumption of accelerator components, accurately predicting the power consumption on new designs from prior optimization estimations. We demonstrate how our approach simplifies the re-use of power optimizations across distinct designs, by leveraging the higher level of design abstraction, using two accelerators representative of the robotics domain, implemented through the Bambu High Level Synthesis tool. Results support the research hypothesis, achieving predictions accurate within +/- 1%.
The development of next-generation communication systems promises to enable extended reality (XR) applications, such as XR gaming with ultra-realistic content and human-grade sensory feedback. These demanding applications impose stringent performance requirements on the underlying wireless communication infrastructure. To meet the expected Quality of Experience (QoE) for XR applications, high-capacity connections are necessary, which can be achieved by using millimeter-wave (mmWave) frequency bands and employing highly directional beams. However, these narrow beams are susceptible to even minor misalignments caused by small-scale user mobility, such as changes in the orientation of the XR head-mounted device (HMD) or minor shifts in user body position. This article explores the impact of small-scale user mobility on mmWave connectivity for XR and reviews approaches to resolve the challenges arising due to small-scale mobility. To deepen our understanding of small-scale mobility during XR usage, we prepared a dataset of user mobility during XR gaming. We use this dataset to study the effects of user mobility on highly directional communication, identifying specific aspects of user mobility that significantly affect the performance of narrow-beam wireless communication systems. Our results confirm the substantial influence of small-scale mobility on beam misalignment, highlighting the need for enhanced mechanisms to effectively manage the consequences of small-scale mobility.
Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
Deep convolutional neural networks (CNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past few years, tremendous progress has been made in this area. In this paper, we survey the recent advanced techniques for compacting and accelerating CNNs model developed. These techniques are roughly categorized into four schemes: parameter pruning and sharing, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and sharing will be described at the beginning, after that the other techniques will be introduced. For each scheme, we provide insightful analysis regarding the performance, related applications, advantages, and drawbacks etc. Then we will go through a few very recent additional successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrix, the main datasets used for evaluating the model performance and recent benchmarking efforts. Finally, we conclude this paper, discuss remaining challenges and possible directions on this topic.
Convolutional networks (ConvNets) have achieved great successes in various challenging vision tasks. However, the performance of ConvNets would degrade when encountering the domain shift. The domain adaptation is more significant while challenging in the field of biomedical image analysis, where cross-modality data have largely different distributions. Given that annotating the medical data is especially expensive, the supervised transfer learning approaches are not quite optimal. In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations. Specifically, our model is based on a dilated fully convolutional network for pixel-wise prediction. Moreover, we build a plug-and-play domain adaptation module (DAM) to map the target input to features which are aligned with source domain feature space. A domain critic module (DCM) is set up for discriminating the feature space of both domains. We optimize the DAM and DCM via an adversarial loss without using any target domain label. Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191