Related papers: G2D: from GTA to Data
As an initial assessment, over 480,000 labeled virtual images of normal highway driving were readily generated in Grand Theft Auto V's virtual environment. Using these images, a CNN was trained to detect following distance to cars/objects…
Video games are a compelling source of annotated data as they can readily provide fine-grained groundtruth for diverse tasks. However, it is not clear whether the synthetically generated data has enough resemblance to the real-world images…
The demand for efficient 3D model generation techniques has grown exponentially, as manual creation of 3D models is time-consuming and requires specialized expertise. While generative models have shown potential in creating 3D textured…
Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world. Previous work has primarily focused on domain randomization and system identification to…
Realistic simulation is critical for applications ranging from robotics to animation. Traditional analytic simulators sometimes struggle to capture sufficiently realistic simulation which can lead to problems including the well known…
Articulated objects are prevalent in daily life. Interactable digital twins of such objects have numerous applications in embodied AI and robotics. Unfortunately, current methods to digitize articulated real-world objects require carefully…
Modern autonomous vehicle simulators feature an ever-growing library of assets, including vehicles, buildings, roads, pedestrians, and more. While this level of customization proves beneficial when creating virtual urban environments, this…
Rain is transparent, which reflects and refracts light in the scene to the camera. In outdoor vision, rain, especially rain streaks degrade visibility and therefore need to be removed. In existing rain streak removal datasets, although…
Digital representations of the real world are being used in many applications, such as augmented reality. 6G systems will not only support use cases that rely on virtual worlds but also benefit from their rich contextual information to…
Simulators are indispensable for research in autonomous systems such as self-driving cars, autonomous robots, and drones. Despite significant progress in various simulation aspects, such as graphical realism, an evident gap persists between…
Screen recordings of mobile applications are easy to obtain and capture a wealth of information pertinent to software developers (e.g., bugs or feature requests), making them a popular mechanism for crowdsourced app feedback. Thus, these…
Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A)…
Recent advancements in Vehicle-to-Everything (V2X) technologies have enabled autonomous vehicles to share sensing information to see through occlusions, greatly boosting the perception capability. However, there are no real-world datasets…
Cars capture and generate huge volumes of data in real-time about the driving dynamics, the environment, and the driver and passengers' activities. Due to the proliferation of cooperative, connected and automated mobility (CCAM), the value…
Navigating large-scale outdoor environments requires complex reasoning in terms of geometric structures, environmental semantics, and terrain characteristics, which are typically captured by onboard sensors such as LiDAR and cameras. While…
Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without…
Realistic simulation is critical for applications ranging from robotics to animation. Learned simulators have emerged as a possibility to capture real world physics directly from video data, but very often require privileged information…
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate and visually plausible representations of the environment.…
We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB…
The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, existing approaches often suffer from a substantial visual and…