Related papers: OccFeat: Self-supervised Occupancy Feature Predict…

Autonomous driving requires accurate and detailed Bird's Eye View (BEV) semantic segmentation for decision making, which is one of the most challenging tasks for high-level scene perception. Feature transformation from frontal view to BEV…

Occupancy prediction provides critical geometric and semantic understanding for robotics but faces efficiency-accuracy trade-offs. Current dense methods suffer computational waste on empty voxels, while sparse query-based approaches lack…

3D occupancy becomes a promising perception representation for autonomous driving to model the surrounding environment at a fine-grained scale. However, it remains challenging to efficiently aggregate 3D occupancy over time across multiple…

Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space. However, most existing studies were conducted under a supervised setup which cannot scale well while handling various new data.…

In this paper, we propose OccTENS, a generative occupancy world model that enables controllable, high-fidelity long-term occupancy generation while maintaining computational efficiency. Different from visual generation, the occupancy world…

Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular,…

Point clouds are crucial for capturing three-dimensional data but often suffer from incompleteness due to limitations such as resolution and occlusion. Traditional methods typically rely on point-based approaches within discriminative…

In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships. However, learning semantic 3D scene graphs in a fully…

Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will…

We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a…

BEV-based 3D perception has emerged as a focal point of research in end-to-end autonomous driving. However, existing BEV approaches encounter significant challenges due to the large feature space, complicating efficient modeling and…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Online Action Detection (OAD) in videos is proposed as a per-frame labeling task to address the real-time prediction tasks that can only obtain the previous and current video frames. This paper presents a novel learning-with-privileged…

Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular due to their wide range of real-world applications, but this task is inherently challenging because of the partial observability of an object…

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…

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model image formation as…

As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view…

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level…

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point's movement. Scene flow estimation is used in various applications such as autonomous driving fields,…

In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection remains inferior to the state-of-the-art (SOTA) of…