Related papers: WildOcc: A Benchmark for Off-Road 3D Semantic Occu…

3D semantic occupancy prediction offers an intuitive and efficient scene understanding and has attracted significant interest in autonomous driving perception. Existing approaches either rely on full supervision, which demands costly…

3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a…

3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models…

Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and severe depth bleeding. We thus introduce ShelfOcc, a…

Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc, a training-free framework for open-vocabulary occupancy prediction from monocular or…

Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this…

3D occupancy prediction (3DOcc) is a rapidly rising and challenging perception task in the field of autonomous driving. Existing 3D occupancy networks (OccNets) are both computationally heavy and label-hungry. In terms of model complexity,…

3D occupancy prediction has become a key perception task in autonomous driving, as it enables comprehensive scene understanding. Recent methods enhance this understanding by incorporating spatiotemporal information through multi-frame…

The resolution of voxel queries significantly influences the quality of view transformation in camera-based 3D occupancy prediction. However, computational constraints and the practical necessity for real-time deployment require smaller…

We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc). GDFusion opens up the underexplored aspects of temporal fusion within the VisionOcc framework, focusing on both temporal cues and…

Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment, making it a critical perception task for autonomous driving. Existing methods either adopt dense grids as scene…

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…

In autonomous vehicles, understanding the surrounding 3D environment of the ego vehicle in real-time is essential. A compact way to represent scenes while encoding geometric distances and semantic object information is via 3D semantic…

Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…

Vision-centric occupancy networks, which represent the surrounding environment with uniform voxels with semantics, have become a new trend for safe driving of camera-only autonomous driving perception systems, as they are able to detect…

Monocular 3D occupancy prediction, aiming to predict the occupancy and semantics within interesting regions of 3D scenes from only 2D images, has garnered increasing attention recently for its vital role in 3D scene understanding.…

This paper introduces VLMFusionOcc3D, a robust multimodal framework for dense 3D semantic occupancy prediction in autonomous driving. Current voxel-based occupancy models often struggle with semantic ambiguity in sparse geometric grids and…

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…

Semantic occupancy has recently gained significant traction as a prominent 3D scene representation. However, most existing methods rely on large and costly datasets with fine-grained 3D voxel labels for training, which limits their…

We present SOccDPT, a memory-efficient approach for 3D semantic occupancy prediction from monocular image input using dense prediction transformers. To address the limitations of existing methods trained on structured traffic datasets, we…