Related papers: LaRa: Latents and Rays for Multi-Camera Bird's-Eye…
Low-cost, vision-centric 3D perception systems for autonomous driving have made significant progress in recent years, narrowing the gap to expensive LiDAR-based methods. The primary challenge in becoming a fully reliable alternative lies in…
Radiance field methods have achieved photorealistic novel view synthesis and geometry reconstruction. But they are mostly applied in per-scene optimization or small-baseline settings. While several recent works investigate feed-forward…
Birds-Eye-View (BEV) segmentation aims to establish a spatial mapping from the perspective view to the top view and estimate the semantic maps from monocular images. Recent studies have encountered difficulties in view transformation due to…
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…
As a cornerstone technique for autonomous driving, Bird's Eye View (BEV) segmentation has recently achieved remarkable progress with pinhole cameras. However, it is non-trivial to extend the existing methods to fisheye cameras with severe…
Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model…
Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods. However, NAT models often suffer from the…
Autonomous driving has garnered significant attention in recent research, and Bird's-Eye-View (BEV) map segmentation plays a vital role in the field, providing the basis for safe and reliable operation. While data augmentation is a commonly…
Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…
LiDAR-based place recognition (LPR) is one of the most crucial components of autonomous vehicles to identify previously visited places in GPS-denied environments. Most existing LPR methods use mundane representations of the input point…
Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that the power of their…
Vehicle perception systems strive to achieve comprehensive and rapid visual interpretation of their surroundings for improved safety and navigation. We introduce YOLO-BEV, an efficient framework that harnesses a unique surrounding cameras…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data. LAVA builds on a few recent innovations to enable adapting to partially labelled datasets with class and domain shifts. First, LAVA…
Autonomous driving has the potential to set the stage for more efficient future mobility, requiring the research domain to establish trust through safe, reliable and transparent driving. Large Language Models (LLMs) possess reasoning…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…
Emerging generative world models and vision-language-action (VLA) systems are rapidly reshaping automated driving by enabling scalable simulation, long-horizon forecasting, and capability-rich decision making. Across these directions,…
Automated Valet Parking (AVP) is a crucial component of advanced autonomous driving systems, focusing on the endpoint task within the "human-vehicle interaction" process to tackle the challenges of the "last mile".The perception module of…
End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals. Recent advanced methods construct a latent…
Autonomous vehicles rely on map information to understand the world around them. However, the creation and maintenance of offline high-definition (HD) maps remains costly. A more scalable alternative lies in online HD map construction,…