Related papers: SOccDPT: Semi-Supervised 3D Semantic Occupancy fro…

We present SemiOccam, an image recognition network that leverages semi-supervised learning in a highly efficient manner. Existing works often rely on complex training techniques and architectures, requiring hundreds of GPU hours for…

Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in autonomous driving due to absence of explicit depth cues in a single RGB image. In this paper, we strive to boost currently underperforming monocular…

Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated…

In the realm of autonomous vehicle perception, comprehending 3D scenes is paramount for tasks such as planning and mapping. Camera-based 3D Semantic Occupancy Prediction (OCC) aims to infer scene geometry and semantics from limited…

Vision-based localization in a prior map is of crucial importance for autonomous vehicles. Given a query image, the goal is to estimate the camera pose corresponding to the prior map, and the key is the registration problem of camera images…

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…

This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discrete occupancy tokens, which inherently…

We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between predicted instance…

With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…

Semantic segmentation and activity classification are key components to creating intelligent surgical systems able to understand and assist clinical workflow. In the Operating Room, semantic segmentation is at the core of creating robots…

Pre-training is a strong strategy for enhancing visual models to efficiently train them with a limited number of labeled images. In semantic segmentation, creating annotation masks requires an intensive amount of labor and time, and…

3D semantic occupancy prediction, which seeks to provide accurate and comprehensive representations of environment scenes, is important to autonomous driving systems. For autonomous cars equipped with multi-camera and LiDAR, it is critical…

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel…

Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection performance by leveraging a large number of unlabeled images alongside a…

Recent self-supervised clustering-based pre-training techniques like DINO and Cribo have shown impressive results for downstream detection and segmentation tasks. However, real-world applications such as autonomous driving face challenges…

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and…

Semi-supervised learning an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires…

3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving. Most existing methods, however, are computationally…

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…

We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupancy prediction and feature distillation tasks. Occupancy…