Related papers: LangOcc: Self-Supervised Open Vocabulary Occupancy…
The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy. Compared with the BEV planes, the 3D semantic occupancy further provides structural…
3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each…
Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during training. Open-vocabulary object detection (OVD) addresses this limitation by leveraging…
Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of…
3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to…
The task of 3D semantic scene completion using monocular cameras is gaining significant attention in the field of autonomous driving. This task aims to predict the occupancy status and semantic labels of each voxel in a 3D scene from…
Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly learn compositional…
The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness,…
The advancement of autonomous driving is increasingly reliant on high-quality annotated datasets, especially in the task of 3D occupancy prediction, where the occupancy labels require dense 3D annotation with significant human effort. In…
3D semantic occupancy prediction is a cornerstone for embodied AI, enabling agents to perceive dense scene geometry and semantics incrementally from monocular video streams. However, current online frameworks face two critical bottlenecks:…
Semantic occupancy prediction enables dense 3D geometric and semantic understanding for autonomous driving. However, existing camera-based approaches implicitly assume complete surround-view observations, an assumption that rarely holds in…
Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation of both semantics and geometry from a single image. Existing…
Occupancy prediction tasks focus on the inference of both geometry and semantic labels for each voxel, which is an important perception mission. However, it is still a semantic segmentation task without distinguishing various instances.…
Occupancy prediction has attracted intensive attention and shown great superiority in the development of autonomous driving systems. The fine-grained environmental representation brought by occupancy prediction in terms of both geometry and…
Panoptic occupancy prediction aims to jointly infer voxel-wise semantics and instance identities within a unified 3D scene representation. Nevertheless, progress in this field remains constrained by the absence of high-quality 3D mesh…
3D visual grounding is a challenging task that often requires direct and dense supervision, notably the semantic label for each object in the scene. In this paper, we instead study the naturally supervised setting that learns from only 3D…
Vision-based 3D semantic occupancy prediction is a critical task in 3D vision that integrates volumetric 3D reconstruction with semantic understanding. Existing methods, however, often rely on modular pipelines. These modules are typically…
Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial…
3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, its effectiveness is inherently constrained in…
3D semantic occupancy prediction is crucial for finely representing the surrounding environment, which is essential for ensuring the safety in autonomous driving. Existing fusion-based occupancy methods typically involve performing a…