4 papers
Generalizable 3D Gaussian Splatting enabled Semantic Coding for Real-Time Immersive Video Communications
Dingxi Yang, Wenqi Guo, Yue Liu +2
Real-time immersive video communications, particularly high-fidelity 3D telepresence, necessitates a synergistic balance between instantaneous dynamic scene reconstruction and high…
Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
Yueh-Cheng Liu, Jozef Hladký, Matthias NieÃner +1
Recent advances in 3D Gaussian Splatting (3DGS) present two main directions: feed-forward models offer fast inference in sparse-view settings, while per-scene optimization yields h…
QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
Yueh-Cheng Liu, Lukas Höllein, Matthias NieÃner +1
Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumet…
TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Dataset
Olaf Wysocki, Benedikt Schwab, Manoj Kumar Biswanath +31
Urban Digital Twins (UDTs) have become essential for managing cities and integrating complex, heterogeneous data from diverse sources. Creating UDTs involves challenges at multiple…