7 papers
AlignGS: Aligning Geometry and Semantics for Robust Indoor Reconstruction from Sparse Views
Yijie Gao, Houqiang Zhong, Tianchi Zhu +3
The demand for semantically rich 3D models of indoor scenes is rapidly growing, driven by applications in augmented reality, virtual reality, and robotics. However, creating them f…
PrismGS: Physically-Grounded Anti-Aliasing for High-Fidelity Large-Scale 3D Gaussian Splatting
Houqiang Zhong, Zhenglong Wu, Sihua Fu +5
3D Gaussian Splatting (3DGS) has recently enabled real-time photorealistic rendering in compact scenes, but scaling to large urban environments introduces severe aliasing artifacts…
4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression
Houqiang Zhong, Zihan Zheng, Qiang Hu +7
Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial inter…
4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
Qiang Hu, Zihan Zheng, Houqiang Zhong +5
3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences. However, the vast number of Gaussians and their associate…
Serial Low-rank Adaptation of Vision Transformer
Houqiang Zhong, Shaocheng Shen, Ke Cai +7
Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computation…
VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression
Qiang Hu, Houqiang Zhong, Zihan Zheng +5
Neural Radiance Field (NeRF)-based volumetric video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video (FVV) experiences that provide audiences with…