Related papers: LeAD-M3D: Leveraging Asymmetric Distillation for R…

Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on…

Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt grid-based vision tokens, which is suboptimal when using…

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of…

Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply…

Off-road autonomous navigation demands reliable 3D perception for robust obstacle detection in challenging unstructured terrain. While LiDAR is accurate, it is costly and power-intensive. Monocular depth estimation using foundation models…

Object detection is the central issue of intelligent traffic systems, and recent advancements in single-vehicle lidar-based 3D detection indicate that it can provide accurate position information for intelligent agents to make decisions and…

Since the introduction of the self-attention mechanism and the adoption of the Transformer architecture for Computer Vision tasks, the Vision Transformer-based architectures gained a lot of popularity in the field, being used for tasks such…

Monocular 3D object detection (M3OD) has long faced challenges due to data scarcity caused by high annotation costs and inherent 2D-to-3D ambiguity. Although various weakly supervised methods and pseudo-labeling methods have been proposed…

Radar-camera fusion methods have emerged as a cost-effective approach for 3D object detection but still lag behind LiDAR-based methods in performance. Recent works have focused on employing temporal fusion and Knowledge Distillation (KD)…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…

Monocular 3D object detection (Mono3D) is a fundamental computer vision task that estimates an object's class, 3D position, dimensions, and orientation from a single image. Its applications, including autonomous driving, augmented reality,…

Unlabeled LiDAR logs, in autonomous driving applications, are inherently a gold mine of dense 3D geometry hiding in plain sight - yet they are almost useless without human labels, highlighting a dominant cost barrier for…

We propose a novel semi-supervised active learning (SSAL) framework for monocular 3D object detection with LiDAR guidance (MonoLiG), which leverages all modalities of collected data during model development. We utilize LiDAR to guide the…

Accurate inter-vehicle distance estimation is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. While LiDAR and radar provide high precision, their high cost prohibits widespread adoption in mass-market…

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

Depth completion involves predicting dense depth maps from sparse LiDAR inputs. However, sparse depth annotations from sensors limit the availability of dense supervision, which is necessary for learning detailed geometric features. In this…

The precise localization of 3D objects from a single image without depth information is a highly challenging problem. Most existing methods adopt the same approach for all objects regardless of their diverse distributions, leading to…

In the field of 3D object detection for autonomous driving, LiDAR-Camera (LC) fusion is the top-performing sensor configuration. Still, LiDAR is relatively high cost, which hinders adoption of this technology for consumer automobiles.…

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…

Learning semantically meaningful representations from unstructured 3D point clouds remains a central challenge in computer vision, especially in the absence of large-scale labeled datasets. While masked point modeling (MPM) is widely used…