神经辐射场（NERF）及其变体在代表3D场景和合成照片现实的小说视角方面取得了巨大成功。但是，它们通常基于针孔摄像头模型，并假设全焦点输入。这限制了它们的适用性，因为从现实世界中捕获的图像通常具有有限的场地（DOF）。为了减轻此问题，我们介绍了DOF-NERF，这是一种新型的神经渲染方法，可以处理浅的DOF输入并可以模拟DOF效应。特别是，它扩展了NERF，以模拟按照几何光学的原理模拟镜头的光圈。这样的物理保证允许DOF-NERF使用不同的焦点配置操作视图。 DOF-NERF受益于显式光圈建模，还可以通过调整虚拟光圈和焦点参数来直接操纵DOF效果。它是插件，可以插入基于NERF的框架中。关于合成和现实世界数据集的实验表明，DOF-NERF不仅在全焦点设置中与NERF相当，而且可以合成以浅DOF输入为条件的全焦点新型视图。还展示了DOF-nerf在DOF渲染上的有趣应用。源代码将在https://github.com/zijinwuzijin/dof-nerf上提供。

Digital Twin is an emerging technology that replicates real-world entities into a digital space. It has attracted increasing attention in the transportation field and many researchers are exploring its future applications in the development of Intelligent Transportation System (ITS) technologies. Connected vehicles (CVs) and pedestrians are among the major traffic participants in ITS. However, the usage of Digital Twin in research involving both CV and pedestrian remains largely unexplored. In this study, a Digital Twin framework for CV and pedestrian in-the-loop simulation is proposed. The proposed framework consists of the physical world, the digital world, and data transmission in between. The features for the entities (CV and pedestrian) that need digital twined are divided into external state and internal state, and the attributes in each state are described. We also demonstrate a sample architecture under the proposed Digital Twin framework, which is based on Carla-Sumo Co-simulation and Cave automatic virtual environment (CAVE). The proposed framework is expected to provide guidance to the future Digital Twin research, and the architecture we build can serve as the testbed for further research and development of ITS applications on CV and pedestrian.

Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we propose a novel approach for this task, which we call Cortex2Image, to decode visual stimuli with high semantic fidelity and rich fine-grained detail. In particular, we train a surface-based convolutional network model that maps from brain response to semantic image features first (Cortex2Semantic). We then combine this model with a high-quality image generator (Instance-Conditioned GAN) to train another mapping from brain response to fine-grained image features using a variational approach (Cortex2Detail). Image reconstructions obtained by our proposed method achieve state-of-the-art semantic fidelity, while yielding good fine-grained similarity with the ground-truth stimulus. Our code is available at: https://github.com/zijin-gu/meshconv-decoding.git.

以安全为导向的研究思想和应用的开发需要精细的车辆轨迹数据，这些数据不仅具有很高的精度，而且还捕获了大量关键安全事件。本文介绍了Citysim数据集，该数据集的设计核心目的是促进基于安全的研究和应用。 Citysim的车辆轨迹从在12个不同位置录制的1140分钟的无人机视频中提取。它涵盖了各种道路几何形状，包括高速公路基本段，编织段，高速公路合并/偏离段，信号交叉点，停止对照的交叉点以及没有符号/信号控制的交叉点。通过五步操作生成CitySim轨迹，以确保轨迹精度。此外，数据集提供了车辆旋转的边界框信息，该信息被证明可以改善安全评估。与其他基于视频的轨迹数据集相比，CitySim数据集的严重性更高，包括切入，合并和分歧事件，其严重性更高。此外，CitySim通过提供相关资产（如记录位置的3D基本地图和信号时间）来促进对数字双胞胎应用的研究。这些功能为安全研究和应用程序提供了更全面的条件，例如自动驾驶汽车安全和基于位置的安全分析。该数据集可在https://github.com/ozheng1993/ucf-sst-citysim-dataset上在线获得。

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving. Given the highly dynamic and variant nature of the input, the visuomotor driving task inherently lacks view and translation invariance, and the visual input contains massive irrelevant information for decision making, resulting in predominant pre-training approaches from general vision less suitable for the autonomous driving task. To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. The proposed PPGeo is performed in two stages to support effective self-supervised training. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only. As such, the pre-trained visual encoder is equipped with rich driving policy related representations and thereby competent for multiple visuomotor driving tasks. Extensive experiments covering a wide span of challenging scenarios have demonstrated the superiority of our proposed approach, where improvements range from 2% to even over 100% with very limited data. Code and models will be available at https://github.com/OpenDriveLab/PPGeo.

In this work, we focus on instance-level open vocabulary segmentation, intending to expand a segmenter for instance-wise novel categories without mask annotations. We investigate a simple yet effective framework with the help of image captions, focusing on exploiting thousands of object nouns in captions to discover instances of novel classes. Rather than adopting pretrained caption models or using massive caption datasets with complex pipelines, we propose an end-to-end solution from two aspects: caption grounding and caption generation. In particular, we devise a joint Caption Grounding and Generation (CGG) framework based on a Mask Transformer baseline. The framework has a novel grounding loss that performs explicit and implicit multi-modal feature alignments. We further design a lightweight caption generation head to allow for additional caption supervision. We find that grounding and generation complement each other, significantly enhancing the segmentation performance for novel categories. We conduct extensive experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS). The results demonstrate the superiority of our CGG framework over previous OVIS methods, achieving a large improvement of 6.8% mAP on novel classes without extra caption data. Our method also achieves over 15% PQ improvements for novel classes on the OSPS benchmark under various settings.

Nearest-Neighbor (NN) classification has been proven as a simple and effective approach for few-shot learning. The query data can be classified efficiently by finding the nearest support class based on features extracted by pretrained deep models. However, NN-based methods are sensitive to the data distribution and may produce false prediction if the samples in the support set happen to lie around the distribution boundary of different classes. To solve this issue, we present P3DC-Shot, an improved nearest-neighbor based few-shot classification method empowered by prior-driven data calibration. Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification. Specifically, we treat the prototypes representing each base class as priors and calibrate each support data based on its similarity to different base prototypes. Then, we perform NN classification using these discretely calibrated support data. Results from extensive experiments on various datasets show our efficient non-learning based method can outperform or at least comparable to SOTA methods which need additional learning steps.

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.