94 citations · 107 across the 4 of their papers we have counts for
5 papers
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
Shuhong Liu, Heng Zhou, Lingfeng Qian +7
Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and e…
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
Heng Zhou, Shuhong Liu, Yonghao He +6
We present X-lens, a compact feed-forward model for metric depth estimation from a variable number of calibrated fisheye and pinhole views. To support real-time downstream percepti…
MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis
Shuhong Liu, Tianchen Deng, Heng Zhou +4
Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete…
MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction
Heng Zhou, Zhetao Guo, Shuhong Liu +4
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for…
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
Mingrui Li, Shuhong Liu, Heng Zhou +4
We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimizati…