Related papers: UFO: Unifying Feed-Forward and Optimization-based …
Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural…
Small Unmanned Aerial Vehicles (UAVs) exhibit immense potential for navigating indoor and hard-to-reach areas, yet their significant constraints in payload and autonomy have largely prevented their use for complex tasks like high-quality…
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…
Object detection in unmanned aerial vehicle (UAV) remote sensing images poses significant challenges due to unstable image quality, small object sizes, complex backgrounds, and environmental occlusions. Small objects, in particular, occupy…
This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising…
Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast to most real-time capable approaches, our approach does not…
Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervision and overlook a…
Multi-camera 3D perception has emerged as a prominent research field in autonomous driving, offering a viable and cost-effective alternative to LiDAR-based solutions. The existing multi-camera algorithms primarily rely on monocular 2D…
Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently…
Many people search for foreground objects to use when editing images. While existing methods can retrieve candidates to aid in this, they are constrained to returning objects that belong to a pre-specified semantic class. We instead propose…
Current end-to-end autonomous driving methods typically learn only from expert planning data collected from a single ego vehicle, severely limiting the diversity of learnable driving policies and scenarios. However, a critical yet…
We introduce UFO, a modular aerial robotic platform for transforming a rigid object into a multirotor robot. To achieve this, we develop flight modules, in the form of a control module and propelling modules, that can be affixed to an…
We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the…
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…
In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second),…
Vehicle trajectory data provides critical information for traffic flow modeling and analysis. Unmanned aerial vehicles (UAV) is an emerging technology for traffic data collection because of its flexibility and diversity on spatial and…
We present the first scene-update aerial path planning algorithm specifically designed for detecting and updating change areas in urban environments. While existing methods for large-scale 3D urban scene reconstruction focus on achieving…
Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small…
We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotated real-world data, forcing a reliance on synthetic…