activity
20242026
collaborators

22 papers

cs.CV2026

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

Yuan Li, Congyi Zhang, Xifeng Gao +1

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based r…

cs.CV2026

SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

Rui Xu, Wenyue Chen, Jiepeng Wang +7

Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a sin…

cs.GR2026

SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces

Chuanxiang Yang, Junhui Hou, Yuan Liu +5

Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that…

cs.CV2026

UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation

Chengfeng Zhao, Junbo Qi, Yulou Liu +6

Simulating physically realistic garment deformations is an essential task for virtual immersive experience, which is often achieved by physics simulation methods. However, these me…

cs.CV2026

BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds

Tongyan Hua, Haoran Gong, Yuan Liu +3

We introduce BuildAnyPoint, a novel generative framework for structured 3D building reconstruction from point clouds with diverse distributions, such as those captured by airborne…

cs.CV2026

MEGS: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning

Jiarui Chen, Yikeng Chen, Yingshuang Zou +5

3D Gaussian Splatting (3DGS) has emerged as a dominant novel-view synthesis technique, but its high memory consumption severely limits its applicability on edge devices. A growing…