Related papers: Graph-DETR3D: Rethinking Overlapping Regions for M…

The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction, which requires complicated indexing of local image-view features via 3D-to-2D projection. Other methods implicitly introduce geometric positional…

Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules…

LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D. However, object detectors face a critical challenge when dealing with unknown foreground…

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches…

This paper proposes 3DGeoDet, a novel geometry-aware 3D object detection approach that effectively handles single- and multi-view RGB images in indoor and outdoor environments, showcasing its general-purpose applicability. The key challenge…

3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work often uses a tracking-by-detection pipeline, where the feature of each object is extracted independently to compute an affinity matrix. Then, the affinity matrix…

We present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image data for 3D detection is resource-intensive and time-consuming.…

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV…

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding,…

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…

3D multi-object tracking is a crucial component in the perception system of autonomous driving vehicles. Tracking all dynamic objects around the vehicle is essential for tasks such as obstacle avoidance and path planning. Autonomous…

Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional grid and sequence-based convolutional and transformer…

Object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. This procedure becomes challenging when target objects are overlapping, are densely clustered, and/or present fuzzy boundaries.…

Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed…

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose…