Related papers: DrivingGaussian++: Towards Realistic Reconstructio…
Editable high-fidelity 4D scenes are crucial for autonomous driving, as they can be applied to end-to-end training and closed-loop simulation. However, existing reconstruction methods are primarily limited to replicating observed scenes and…
Gaussian splatting demonstrates proficiency for 3D scene modeling but suffers from substantial data volume due to inherent primitive redundancy. To enable future photorealistic 3D immersive visual communication applications, significant…
Road surface reconstruction is essential for autonomous driving, supporting centimeter-accurate lane perception and high-definition mapping in complex urban environments.While recent methods based on mesh rendering or 3D Gaussian splatting…
The goal of traffic simulation is to augment a potentially limited amount of manually-driven miles that is available for testing and validation, with a much larger amount of simulated synthetic miles. The culmination of this vision would be…
Reconstructing dynamic scenes from Vehicle-to-Infrastructure Cooperative Autonomous Driving (VICAD) data is fundamentally complicated by temporal asynchrony: vehicle and infrastructure cameras operate on independent clocks, capturing the…
We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture bringing a immersive quality to the viewing experience. Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS)…
High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but generating these models in cluttered dealership drive-throughs presents severe technical challenges. Unlike static-scene…
Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster…
Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios,…
We present ReinDriveGen, a framework that enables full controllability over dynamic driving scenes, allowing users to freely edit actor trajectories to simulate safety-critical corner cases such as front-vehicle collisions, drifting cars,…
We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian…
The novel Dynamic Vision Sensors (DVSs) gained a great amount of attention recently as they are superior compared to RGB cameras in terms of latency, dynamic range and energy consumption. This is particularly of interest for autonomous…
A single-pass driving clip frequently results in incomplete scanning of the road structure, making reconstructed scene expanding a critical requirement for sensor simulators to effectively regress driving actions. Although contemporary 3D…
Existing Gaussian splatting methods often fall short in achieving satisfactory novel view synthesis in driving scenes, primarily due to the absence of crafty designs and geometric constraints for the involved elements. This paper introduces…
Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan…
The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time across various…
We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process, obviating the need for 3D data.…
State-of-the-art novel view synthesis methods achieve impressive results for multi-view captures of static 3D scenes. However, the reconstructed scenes still lack "liveliness," a key component for creating engaging 3D experiences. Recently,…
Robust and realistic rendering for large-scale road scenes is essential in autonomous driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking progress in neural rendering, but the general fidelity of large-scale…
We present LiDAR-GS, a Gaussian Splatting (GS) method for real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes. Recent GS methods proposed for cameras have achieved significant advancements in real-time…