Related papers: RendBEV: Semantic Novel View Synthesis for Self-Su…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging. Many recent studies on point cloud pre-training, however, have overlooked the issue of incompleteness, where…

3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ…

The performance of object detection methods based on LiDAR information is heavily impacted by the availability of training data, usually limited to certain laser devices. As a result, the use of synthetic data is becoming popular when…

This report describes the winning solution to the Robust Vision Challenge (RVC) semantic segmentation track at ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses SegFormer as the segmentation framework. The model is…

Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution. In this work, we consider…

Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem. In…

Bird's eye view (BEV) representation is a new perception formulation for autonomous driving, which is based on spatial fusion. Further, temporal fusion is also introduced in BEV representation and gains great success. In this work, we…

End-to-end autonomous driving offers a streamlined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained…

LiDAR semantic segmentation models are typically trained from random initialization as universal pre-training is hindered by the lack of large, diverse datasets. Moreover, most point cloud segmentation architectures incorporate custom…

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D…

We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked…

This paper introduces BEV-VLM, a novel approach for trajectory planning in autonomous driving that leverages Vision-Language Models (VLMs) with Bird's-Eye View (BEV) feature maps as visual input. Unlike conventional trajectory planning…

Robust and accurate localization is critical for autonomous driving. Traditional GNSS-based localization methods suffer from signal occlusion and multipath effects in urban environments. Meanwhile, methods relying on high-definition (HD)…

Semantic segmentation networks, which are essential for robotic perception, often suffer from performance degradation when the visual distribution of the deployment environment differs from that of the source dataset on which they were…

Sensing surroundings plays a crucial role in human spatial perception, as it extracts the spatial configuration of objects as well as the free space from the observations. To facilitate the robot perception with such a surrounding sensing…

In autonomous driving, trajectory prediction is essential for safe and efficient navigation. While recent methods often rely on high-definition (HD) maps to provide structured environmental priors, such maps are costly to maintain,…

Road intersection monitoring and control research often utilize bird's eye view (BEV) simulators. In real traffic settings, achieving a BEV akin to that in a simulator necessitates the deployment of drones or specific sensor mounting, which…

Multi-view image generation in autonomous driving demands consistent 3D scene understanding across camera views. Most existing methods treat this problem as a 2D image set generation task, lacking explicit 3D modeling. However, we argue…

Open-Vocabulary Segmentation (OVS) methods are capable of performing semantic segmentation without relying on a fixed vocabulary, and in some cases, without training or fine-tuning. However, OVS methods typically require a human in the loop…