Yang Li

Xuechao Chen, Ying Chen, Jialin Li et al.

3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data scaling challenges. In this work, we introduce a novel self-supervised pre-training framework that incorporates millions of images into 3D pre-training corpora by leveraging a large depth estimation model. New pre-training corpora encounter new challenges in representation ability and embedding efficiency of models. Previous pre-training methods rely on farthest point sampling and k-nearest neighbors to embed a fixed number of 3D tokens. However, these approaches prove inadequate when it comes to embedding millions of samples that feature a diverse range of point numbers, spanning from 1,000 to 100,000. In contrast, we propose a tokenizer with linear-time complexity, which enables the efficient embedding of a flexible number of tokens. Accordingly, a new 3D reconstruction target is proposed to cooperate with our 3D tokenizer. Our method achieves state-of-the-art performance in 3D classification, few-shot learning, and 3D segmentation. Code is available at https://github.com/XuechaoChen/P3P-MAE.

Yongzhi Xu, Yonhon Ng, Yifu Wang et al.

3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating interactive and playable 3D game scenes, all from the user's casual prompts such as a hand-drawn sketch. Sketch-based input offers a natural, and convenient way to convey the user's design intention in the content creation process. To circumvent the data-deficient challenge in learning (i.e. the lack of large training data of 3D scenes), our method leverages a pre-trained 2D denoising diffusion model to generate a 2D image of the scene as the conceptual guidance. In this process, we adopt the isometric projection mode to factor out unknown camera poses while obtaining the scene layout. From the generated isometric image, we use a pre-trained image understanding method to segment the image into meaningful parts, such as off-ground objects, trees, and buildings, and extract the 2D scene layout. These segments and layouts are subsequently fed into a procedural content generation (PCG) engine, such as a 3D video game engine like Unity or Unreal, to create the 3D scene. The resulting 3D scene can be seamlessly integrated into a game development environment and is readily playable. Extensive tests demonstrate that our method can efficiently generate high-quality and interactive 3D game scenes with layouts that closely follow the user's intention.

Qing Zhang, Bing Xu, Xudong Zhang et al.

The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to the emergence of a new research area known as Automatic Prompt Optimization (APO), which develops rapidly in recent years. Existing APO methods such as those based on evolutionary algorithms or trial-and-error approaches realize an efficient and accurate prompt optimization to some extent. However, those researches focus on a single model or algorithm for the generation strategy and optimization process, which limits their performance when handling complex tasks. To address this, we propose a novel framework called Ensemble Learning based Prompt Optimization (ELPO) to achieve more accurate and robust results. Motivated by the idea of ensemble learning, ELPO conducts voting mechanism and introduces shared generation strategies along with different search methods for searching superior prompts. Moreover, ELPO creatively presents more efficient algorithms for the prompt generation and search process. Experimental results demonstrate that ELPO outperforms state-of-the-art prompt optimization methods across different tasks, e.g., improving F1 score by 7.6 on ArSarcasm dataset.

Yang Li, Linbo Li, Daiheng Ni

This paper applies the pareto-optimal concept to LC (lane-changing) motion planning in the presence of mixed traffic including manual and autonomous vehicles. Firstly, a multiobjective optimization problem is presented, in which the comfort, efficiency and safety of the LC vehicle and the surrounding vehicles are jointly modelled. Thereafter, the pareto-optimal solutions are obtained through employing the NSGA-II (Non-dominated Sorting Genetic -II) algorithm. Finally, the experiment section analyzes the (macroscopic and microscopic) lane-changing impact from a pareto-optimal perspective. Also, a comprehensive sensitivity analysis is conducted. Our results demonstrate that our algorithm could significantly reduce the lane-changing impact within its region, and the total costs are reduced in the range of 10.94% to 48.66%. This paper could be considered as a preliminary research framework for the application of the pareto-optimal concept. We hope this research will provide valuable insights into autonomous driving technology.

Yang Li, Linbo Li, Daiheng Ni

Lane-changing (LC) behavior describes the lateral movement of the vehicle from the current-lane to the target-lane while proceeding forward. Among the many research directions, LC duration (LCD) measures the total time it takes for a vehicle to travel from the current lane to the target lane, which is an indispensable indicator to characterize the LC behavior. Although existing research has made some achievements, less attention has been paid to the research of heavy vehicles' LCD. Therefore, this paper aims to further explore the LCD between heavy vehicles and passenger cars. LC trajectories are extracted from the newly-released HighD dataset, which contains of 16.5 hours of measurement and over 11,000 vehicles. The survival function of LCD has been estimated, and the characteristic has been analyzed. Thereafter, the Accelerated Failure Time model is introduced to explore the influencing factors. Results demonstrate that the MST value of passenger cars and heavy vehicles is about 5.51s and 6.08s. The heavy vehicles would maintain a longer time-headway and distance-headway with preceding vehicle when performing LC. Nevertheless, these two factors do not significantly affect the LCD of heavy vehicles. Finally, the results and the modeling implications have been discussed. We hope this paper could contribute to our further understanding of the LC behaviors for heavy vehicles and passenger cars.