12 papers
MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
Shuzhao Xie, Junchen Ge, Weixiang Zhang +10
3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-t…
Tail-Aware Post-Training Quantization for 3D Geometry Models
Sicheng Pan, Chen Tang, Shuzhao Xie +6
The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization (PTQ) enabl…
VGGT-DP: Generalizable Robot Control via Vision Foundation Models
Shijia Ge, Yijun Liu, Yinxin Zhang +4
Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often negle…
SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
Wei Yao, Shuzhao Xie, Letian Li +5
Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and th…
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
Mingzi Wang, Yuan Meng, Chen Tang +9
The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance an…
Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification
Shijia Ge, Weixiang Zhang, Shuzhao Xie +2
Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our…
EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
Weixiang Zhang, Shuzhao Xie, Chengwei Ren +5
We propose EVOlutionary Selector (EVOS), an efficient training paradigm for accelerating Implicit Neural Representation (INR). Unlike conventional INR training that feeds all sampl…
Enhancing Implicit Neural Representations via Symmetric Power Transformation
Weixiang Zhang, Shuzhao Xie, Chengwei Ren +3
We propose symmetric power transformation to enhance the capacity of Implicit Neural Representation~(INR) from the perspective of data transformation. Unlike prior work utilizing r…
SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming
Shuzhao Xie, Jiahang Liu, Weixiang Zhang +7
Recent advances in 3D Gaussian Splatting (3DGS) have greatly improved 3D reconstruction. However, its substantial data size poses a significant challenge for transmission and stora…
MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation
Shuzhao Xie, Weixiang Zhang, Chen Tang +4
3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the huge file size of the 3D Gaussians presents challenges for transmission an…
Expansive Supervision for Neural Radiance Field
Weixiang Zhang, Shuzhao Xie, Shijia Ge +3
Neural Radiance Field (NeRF) has achieved remarkable success in creating immersive media representations through its exceptional reconstruction capabilities. However, the computati…
Tuning-Free Visual Customization via View Iterative Self-Attention Control
Xiaojie Li, Chenghao Gu, Shuzhao Xie +3
Fine-Tuning Diffusion Models enable a wide range of personalized generation and editing applications on diverse visual modalities. While Low-Rank Adaptation (LoRA) accelerates the…