Related papers: FB-OCC: 3D Occupancy Prediction based on Forward-B…

End-to-end autonomous driving systems increasingly rely on vision-centric world models to understand and predict their environment. However, a common ineffectiveness in these models is the full reconstruction of future scenes, which expends…

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…

3D semantic occupancy and flow prediction are fundamental to spatiotemporal scene understanding. This paper proposes a vision-based framework with three targeted improvements. First, we introduce an occlusion-aware adaptive lifting…

Predicting variations in complex traffic environments is crucial for the safety of autonomous driving. Recent advancements in occupancy forecasting have enabled forecasting future 3D occupied status in driving environments by observing…

3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy…

While multi-modal 3D semantic occupancy prediction typically enhances robustness by fusing camera and LiDAR inputs, its effectiveness is fundamentally constrained by environmental variability. Specifically, camera sensors suffer from severe…

Self-supervision for semantic occupancy estimation is appealing as it removes the labour-intensive manual annotation, thus allowing one to scale to larger autonomous driving datasets. Superquadrics offer an expressive shape family very…

3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation…

Autonomous driving without high-definition (HD) maps demands a higher level of active scene understanding. In this competition, the organizers provided the multi-perspective camera images and standard-definition (SD) maps to explore the…

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…

Autonomous driving requires a persistent understanding of 3D scenes that is robust to temporal disturbances and accounts for potential future actions. We introduce a new concept of 4D Occupancy Spatio-Temporal Persistence (OccSTeP), which…

Seeing only a tiny part of the whole is not knowing the full circumstance. Bird's-eye-view (BEV) perception, a process of obtaining allocentric maps from egocentric views, is restricted when using a narrow Field of View (FoV) alone. In this…

Monocular 3D detection is a challenging task due to the lack of accurate 3D information. Existing approaches typically rely on geometry constraints and dense depth estimates to facilitate the learning, but often fail to fully exploit the…

Developing 3D semantic occupancy prediction models often relies on dense 3D annotations for supervised learning, a process that is both labor and resource-intensive, underscoring the need for label-efficient or even label-free approaches.…

Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has…

The advent of deep learning has led to significant progress in monocular human reconstruction. However, existing representations, such as parametric models, voxel grids, meshes and implicit neural representations, have difficulties…

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…

Detection of moving objects is a very important task in autonomous driving systems. After the perception phase, motion planning is typically performed in Bird's Eye View (BEV) space. This would require projection of objects detected on the…

Language-conditioned local navigation requires a robot to infer a nearby traversable target location from its current observation and an open-vocabulary, relational instruction. Existing vision-language spatial grounding methods usually…