Related papers: SHTOcc: Effective 3D Occupancy Prediction with Spa…
Autonomous driving requires forecasting both geometry and semantics over time to effectively reason about future environment states. Existing vision-based occupancy forecasting methods focus on motion-related categories such as static and…
Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class…
Efficient data access in High-Performance Computing (HPC) systems is essential to the performance of intensive computing tasks. Traditional optimizations of the I/O stack aim to improve peak performance but are often workload specific and…
Visual grounding aims to identify objects or regions in a scene based on natural language descriptions, essential for spatially aware perception in autonomous driving. However, existing visual grounding tasks typically depend on bounding…
3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing methods struggle with geometric misalignment in view…
In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023. Existing methods for occupancy prediction primarily focus on…
LiDAR-based 3D occupancy prediction evolved rapidly alongside the emergence of large datasets. Nevertheless, the potential of existing diverse datasets remains underutilized as they kick in individually. Models trained on a specific dataset…
In real-world data, long-tailed data distribution is common, making it challenging for models trained on empirical risk minimisation to learn and classify tail classes effectively. While many studies have sought to improve long tail…
This paper introduces InverseMatrixVT3D, an efficient method for transforming multi-view image features into 3D feature volumes for 3D semantic occupancy prediction. Existing methods for constructing 3D volumes often rely on depth…
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision…
Spatio-Temporal Scene Graphs (STSGs) provide a concise and expressive representation of dynamic scenes by modeling objects and their evolving relationships over time. However, real-world visual relationships often exhibit a long-tailed…
3D occupancy infers fine-grained 3D geometry and semantics which is critical for autonomous driving. Most existing approaches carry high compute costs, requiring dense 3D feature volume and cross-attention to effectively aggregate…
Multimodal 3D occupancy prediction has garnered significant attention for its potential in autonomous driving. However, most existing approaches are single-modality: camera-based methods lack depth information, while LiDAR-based methods…
Occupancy and 3D object detection are characterized as two standard tasks in modern autonomous driving system. In order to deploy them on a series of edge chips with better precision and time-consuming trade-off, contemporary approaches…
Real-world data are long-tailed, the lack of tail samples leads to a significant limitation in the generalization ability of the model. Although numerous approaches of class re-balancing perform well for moderate class imbalance problems,…
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail…
3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they…
We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as…
Recently, multimodal large language models (MM-LLMs) have achieved significant success in various tasks, but their high computational costs limit widespread application. The main computational burden arises from processing concatenated text…
Reliably predicting future occupancy of highly dynamic urban environments is an important precursor for safe autonomous navigation. Common challenges in the prediction include forecasting the relative position of other vehicles, modelling…