Related papers: G2D: from GTA to Data
An accurate understanding of a self-driving vehicle's surrounding environment is crucial for its navigation system. To enhance the effectiveness of existing algorithms and facilitate further research, it is essential to provide…
Reconstructing outdoor 3D scenes from temporal observations is a challenge that recent work on neural fields has offered a new avenue for. However, existing methods that recover scene properties, such as geometry, appearance, or radiance,…
A free-viewpoint, editable, and high-fidelity driving simulator is crucial for training and evaluating end-to-end autonomous driving systems. In this paper, we present GA-Drive, a novel simulation framework capable of generating camera…
4D radars, which provide 3D point cloud data along with Doppler velocity, are attractive components of modern automated driving systems due to their low cost and robustness under adverse weather conditions. However, they provide a…
Understanding occupant-vehicle interactions by modeling control transitions is important to ensure safe approaches to passenger vehicle automation. Models which contain contextual, semantically meaningful representations of driver states…
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more…
Utilizing well-trained representations in transfer learning often results in superior performance and faster convergence compared to training from scratch. However, even if such good representations are transferred, a model can easily…
Common computer vision systems typically assume ideal pinhole cameras but fail when facing real-world camera effects such as fisheye distortion and rolling shutter, mainly due to the lack of learning from training data with camera effects.…
Millions of network cameras have been deployed worldwide. Real-time data from many network cameras can offer instant views of multiple locations with applications in public safety, transportation management, urban planning, agriculture,…
Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes,…
Recent works have been exploring the scaling laws in the field of Embodied AI. Given the prohibitive costs of collecting real-world data, we believe the Simulation-to-Real (Sim2Real) paradigm is a crucial step for scaling the learning of…
3D data simulation aims to bridge the gap between simulated and real-captured 3D data, which is a fundamental problem for real-world 3D visual tasks. Most 3D data simulation methods inject predefined physical priors but struggle to capture…
Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited…
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges,…
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios. Our aim is to contribute to the development of…
Accurate 6D pose estimation has gained more attention over the years for robotics-assisted tasks that require precise interaction with physical objects. This paper presents an interactive 3D-to-2D visualization and annotation tool to…
Learning transferable knowledge from unlabeled video data and applying it in new environments is a fundamental capability of intelligent agents. This work presents VideoWorld 2, which extends VideoWorld and offers the first investigation…
Vehicle-to-everything (V2X) communication is a key technology for enabling intelligent transportation systems (ITS) that can improve road safety, traffic efficiency, and environmental sustainability. Among the various V2X applications,…
This paper introduces a novel pipeline for generating large-scale, highly realistic, and automatically labeled datasets for computer vision tasks in robotic environments. Our approach addresses the critical challenges of the domain gap…
Realistic modeling of vehicular mobility has been particularly challenging due to a lack of large libraries of measurements in the research community. In this paper we introduce a novel method for large-scale monitoring, analysis, and…