Note: The Conda CUDA and system CUDA versions may differ. The compiler version (nvcc) is what matters for PyTorch extensions compilation (diff-gaussian-rasterization_fastgs). The MipNeRF360 scenes are ...

Abstract: Accurate and efficient lane detection in 3D space is essential for autonomous driving systems, where robust generalization is the foremost requirement for 3D lane detection algorithms.

While Multimodal Large Language Models demonstrate strong semantic capabilities, they often suffer from spatial blindness and struggle with fine-grained geometric reasoning and physical dynamics.

Abstract: Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many ...