6 papers
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
NVIDIA, :, Jiahui Huang +14
3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent yea…
LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision
Yiming Huang, Xin Kang, Sipeng Zhang +3
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time LiDAR and camera synthesis in autonomous driving simulation. However, simulating LiDAR with 3DGS rema…
SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
Haithem Turki, Qi Wu, Xin Kang +5
Rigorous testing of autonomous robots, such as self-driving vehicles, is essential to ensure their safety in real-world deployments. This requires building high-fidelity simulators…
LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework
Xin Kang, Zihan Zheng, Lei Chu +5
We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diff…
ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery
Yanzhe Lyu, Kai Cheng, Xin Kang +1
Recently, 3D Gaussian Splatting (3D-GS) has prevailed in novel view synthesis, achieving high fidelity and efficiency. However, it often struggles to capture rich details and compl…
Region-Enhanced Feature Learning for Scene Semantic Segmentation
Xin Kang, Chaoqun Wang, Xuejin Chen
Semantic segmentation in complex scenes relies not only on object appearance but also on object location and the surrounding environment. Nonetheless, it is difficult to model long…