5 papers
E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
Wenyan Cong, Yiqing Liang, Yancheng Zhang +7
Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enable…
Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors
Lanqing Guo, Yufei Wang, Hezhen Hu +4
Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussia…
Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
Longfei Li, Zhiwen Fan, Wenyan Cong +10
Synthesizing realistic Martian landscape videos is crucial for mission rehearsal and robotic simulation. However, this task poses unique challenges due to the scarcity of high-qual…
Demystifying the Visual Quality Paradox in Multimodal Large Language Models
Shuo Xing, Lanqing Guo, Hongyuan Hua +5
Recent Multimodal Large Language Models (MLLMs) excel on benchmark vision-language tasks, yet little is known about how input visual quality shapes their responses. Does higher per…
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
Shuo Xing, Hongyuan Hua, Xiangbo Gao +10
Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeni…