MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving

In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which predict and generate future environmental states, offer a promising solution by synthesizing annotated video data for training. However, existing methods struggle to generate long, consistent videos without accumulating errors, especially in dynamic scenes. To address this, we propose MiLA, a novel framework for generating high-fidelity, long-duration videos up to one minute. MiLA utilizes a Coarse-to-Re(fine) approach to both stabilize video generation and correct distortion of dynamic objects. Additionally, we introduce a Temporal Progressive Denoising Scheduler and Joint Denoising and Correcting Flow modules to improve the quality of generated videos. Extensive experiments on the nuScenes dataset show that MiLA achieves state-of-the-art performance in video generation quality. For more information, visit the project website: https://github.com/xiaomi-mlab/mila.github.io.

Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios

Ensuring the safety of autonomous vehicles necessitates comprehensive simulation of multi-sensor data, encompassing inputs from both cameras and LiDAR sensors, across various dynamic driving scenarios. Neural rendering techniques, which utilize collected raw sensor data to simulate these dynamic environments, have emerged as a leading methodology. While NeRF-based approaches can uniformly represent scenes for rendering data from both camera and LiDAR, they are hindered by slow rendering speeds due to dense sampling. Conversely, Gaussian Splatting-based methods employ Gaussian primitives for scene representation and achieve rapid rendering through rasterization. However, these rasterization-based techniques struggle to accurately model non-linear optical sensors. This limitation restricts their applicability to sensors beyond pinhole cameras. To address these challenges and enable unified representation of dynamic driving scenarios using Gaussian primitives, this study proposes a novel hybrid approach. Our method utilizes rasterization for rendering image data while employing Gaussian ray-tracing for LiDAR data rendering. Experimental results on public datasets demonstrate that our approach outperforms current state-of-the-art methods. This work presents a unified and efficient solution for realistic simulation of camera and LiDAR data in autonomous driving scenarios using Gaussian primitives, offering significant advancements in both rendering quality and computational efficiency.

Learning A Zero-shot Occupancy Network from Vision Foundation Models via Self-supervised Adaptation

Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this work proposes a novel approach that bridges 2D vision foundation models (VFMs) with 3D tasks by decoupling 3D supervision into an ensemble of image-level primitives, e.g., semantic and geometric components. As a key motivator, we leverage the zero-shot capabilities of vision-language models for image semantics. However, due to the notorious ill-posed problem - multiple distinct 3D scenes can produce identical 2D projections, directly inferring metric depth from a monocular image in a zero-shot manner is unsuitable. In contrast, 2D VFMs provide promising sources of relative depth, which theoretically aligns with metric depth when properly scaled and offset. Thus, we adapt the relative depth derived from VFMs into metric depth by optimising the scale and offset using temporal consistency, also known as novel view synthesis, without access to ground-truth metric depth. Consequently, we project the semantics into 3D space using the reconstructed metric depth, thereby providing 3D supervision. Extensive experiments on nuScenes and SemanticKITTI demonstrate the effectiveness of our framework. For instance, the proposed method surpasses the current state-of-the-art by 3.34% mIoU on nuScenes for voxel occupancy prediction.

Cross-platform Prediction of Depression Treatment Outcome Using Location Sensory Data on Smartphones

Currently, depression treatment relies on closely monitoring patients response to treatment and adjusting the treatment as needed. Using self-reported or physician-administrated questionnaires to monitor treatment response is, however, burdensome, costly and suffers from recall bias. In this paper, we explore using location sensory data collected passively on smartphones to predict treatment outcome. To address heterogeneous data collection on Android and iOS phones, the two predominant smartphone platforms, we explore using domain adaptation techniques to map their data to a common feature space, and then use the data jointly to train machine learning models. Our results show that this domain adaptation approach can lead to significantly better prediction than that with no domain adaptation. In addition, our results show that using location features and baseline self-reported questionnaire score can lead to F1 score up to 0.67, comparable to that obtained using periodic self-reported questionnaires, indicating that using location data is a promising direction for predicting depression treatment outcome.

Separating Drone Point Clouds From Complex Backgrounds by Cluster Filter -- Technical Report for CVPR 2024 UG2 Challenge

The increasing deployment of small drones as tools of conflict and disruption has amplified their threat, highlighting the urgent need for effective anti-drone measures. However, the compact size of most drones presents a significant challenge, as traditional supervised point cloud or image-based object detection methods often fail to identify such small objects effectively. This paper proposes a simple UAV detection method using an unsupervised pipeline. It uses spatial-temporal sequence processing to fuse multiple lidar datasets effectively, tracking and determining the position of UAVs, so as to detect and track UAVs in challenging environments. Our method performs front and rear background segmentation of point clouds through a global-local sequence clusterer and parses point cloud data from both the spatial-temporal density and spatial-temporal voxels of the point cloud. Furthermore, a scoring mechanism for point cloud moving targets is proposed, using time series detection to improve accuracy and efficiency. We used the MMAUD dataset, and our method achieved 4th place in the CVPR 2024 UG2+ Challenge, confirming the effectiveness of our method in practical applications.

Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models

Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis. However, data analysts often encounter two primary challenges: (1) the need to craft SQL queries skillfully, and (2) the requirement to generate suitable visualization types that enhance the interpretation of query results. Due to its significance, substantial research efforts have been made to explore different approaches to address these challenges, including leveraging large language models (LLMs). However, existing methods fail to meet real-world data exploration requirements primarily due to (1) complex database schema; (2) unclear user intent; (3) limited cross-domain generalization capability; and (4) insufficient end-to-end text-to-visualization capability. This paper presents TiInsight, an automated SQL-based cross-domain exploratory data analysis system. First, we propose hierarchical data context (i.e., HDC), which leverages LLMs to summarize the contexts related to the database schema, which is crucial for open-world EDA systems to generalize across data domains. Second, the EDA system is divided into four components (i.e., stages): HDC generation, question clarification and decomposition, text-to-SQL generation (i.e., TiSQL), and data visualization (i.e., TiChart). Finally, we implemented an end-to-end EDA system with a user-friendly GUI interface in the production environment at PingCAP. We have also open-sourced all APIs of TiInsight to facilitate research within the EDA community. Through extensive evaluations by a real-world user study, we demonstrate that TiInsight offers remarkable performance compared to human experts. Specifically, TiSQL achieves an execution accuracy of 86.3% on the Spider dataset using GPT-4. It also demonstrates state-of-the-art performance on the Bird dataset.

Mini-Splatting2: Building 360 Scenes within Minutes via Aggressive Gaussian Densification

In this study, we explore the essential challenge of fast scene optimization for Gaussian Splatting. Through a thorough analysis of the geometry modeling process, we reveal that dense point clouds can be effectively reconstructed early in optimization through Gaussian representations. This insight leads to our approach of aggressive Gaussian densification, which provides a more efficient alternative to conventional progressive densification methods. By significantly increasing the number of critical Gaussians, we enhance the model capacity to capture dense scene geometry at the early stage of optimization. This strategy is seamlessly integrated into the Mini-Splatting densification and simplification framework, enabling rapid convergence without compromising quality. Additionally, we introduce visibility culling within Gaussian Splatting, leveraging per-view Gaussian importance as precomputed visibility to accelerate the optimization process. Our Mini-Splatting2 achieves a balanced trade-off among optimization time, the number of Gaussians, and rendering quality, establishing a strong baseline for future Gaussian-Splatting-based works. Our work sets the stage for more efficient, high-quality 3D scene modeling in real-world applications, and the code will be made available no matter acceptance.

PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation

The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects effectively. In this paper, we integrate two prevalent methods, masked point modeling (MPM) and 3D-to-2D generation, as pretext tasks within a pre-training framework. We leverage the spatial awareness and precise supervision offered by these two methods to address their respective limitations: ambiguous supervision signals and insensitivity to geometric information. Specifically, the proposed framework, abbreviated as PointCG, consists of a Hidden Point Completion (HPC) module and an Arbitrary-view Image Generation (AIG) module. We first capture visible points from arbitrary views as inputs by removing hidden points. Then, HPC extracts representations of the inputs with an encoder and completes the entire shape with a decoder, while AIG is used to generate rendered images based on the visible points' representations. Extensive experiments demonstrate the superiority of the proposed method over the baselines in various downstream tasks. Our code will be made available upon acceptance.

Physics-informed Shadowgraph Network: An End-to-end Density Field Reconstruction Method

This study presents a novel approach for quantificationally reconstructing density fields from shadowgraph images using physics-informed neural networks

Deep Learning-Driven Microstructure Characterization and Vickers Hardness Prediction of Mg-Gd Alloys

In the field of materials science, exploring the relationship between composition, microstructure, and properties has long been a critical research focus. The mechanical performance of solid-solution Mg-Gd alloys is significantly influenced by Gd content, dendritic structures, and the presence of secondary phases. To better analyze and predict the impact of these factors, this study proposes a multimodal fusion learning framework based on image processing and deep learning techniques. This framework integrates both elemental composition and microstructural features to accurately predict the Vickers hardness of solid-solution Mg-Gd alloys. Initially, deep learning methods were employed to extract microstructural information from a variety of solid-solution Mg-Gd alloy images obtained from literature and experiments. This provided precise grain size and secondary phase microstructural features for performance prediction tasks. Subsequently, these quantitative analysis results were combined with Gd content information to construct a performance prediction dataset. Finally, a regression model based on the Transformer architecture was used to predict the Vickers hardness of Mg-Gd alloys. The experimental results indicate that the Transformer model performs best in terms of prediction accuracy, achieving an R^2 value of 0.9. Additionally, SHAP analysis identified critical values for four key features affecting the Vickers hardness of Mg-Gd alloys, providing valuable guidance for alloy design. These findings not only enhance the understanding of alloy performance but also offer theoretical support for future material design and optimization.