LangSplat: 3D Language Gaussian Splatting

Minghan Qin*, Wanhua Li*†, Jiawei Zhou*, Haoqian Wang†, Hanspeter Pfister

• We introduces LangSplat, which constructs a 3D language field that enables precise and efficient open-vocabulary querying within 3D spaces.

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Wanhua Li*, Yujie Zhao*, Minghan Qin*, Yang Liu, Yuanhao Cai, Chuang Gan, Hanspeter Pfister

• We present LangSplatV2, which achieves high-dimensional feature splatting at 476.2 FPS and 3D open-vocabulary text querying at 384.6 FPS for high-resolution images.

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models

Wanhua Li*, Renping Zhou*, Jiawei Zhou, Yingwei Song, Johannes Herter, Minghan Qin, Gao Huang, Hanspeter Pfister

• We present 4D LangSplat, an approach to constructing a dynamic 4D language field in evolving scenes, leveraging Multimodal Large Language Models.

LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding

Hao Li*, Minghan Qin*†, Zhengyu Zou*, Diqi He, Bohan Li, Bingquan Dai, Dingwen Zhang†, Junwei Han

• We propose LangSurf, a model that aligns language features with object surfaces to enhance 3D scene understanding

SLGaussian: Fast Language Gaussian Splatting in Sparse Views

Kangjie Chen*, Bingquan Dai*, Minghan Qin, Dongbin Zhang, Peihao Li, Yingshuang Zou, Haoqian Wang†

• We propose SLGaussian, a feed-forward method for constructing 3D semantic fields from sparse viewpoints, allowing direct inference of 3DGS-based scenes.

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Bingquan Dai*, Li Ray Luo*, Qihong Tang, Jie Wang, Xinyu Lian, Hao Xu, Minghan Qin, Xudong Xu, Bo Dai, Haoqian Wang†, Zhaoyang Lyu†, Jiangmiao Pang

• MeshCoder generates structured mesh code from 3D point clouds, enhancing shape editing and understanding.

VAP: Precise Action-to-Video Generation through Visual Action Prompts

Yuang Wang, Chao Wen, Haoyu Guo, Sida Peng, Minghan Qin, Hujun Bao, Xiaowei Zhou, Ruizhen Hu

• VAP harnesses subject renderings as action proxies for interactive video generation, striking an balance between precision and generality in action representation.

NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation

Yuxiao Yang, Peihao Li, Yuhong Zhang, Junzhe Lu, Xianglong He, Minghan Qin, Weitao Wang, Haoqian Wang†

• NOVA3D unleashes geometric 3D prior from a video diffusion model to generate high-quality textured meshes from input image.

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Yang Li, Minghan Qin, Yu Li, Haoqian Wang

• For each single image with a tracked pose, GUAVA can reconstruct a 3D upper-body Gaussian avatar via feed-forward inference within sub-second time, enabling real-time expressive animation and novel view synthesis at 512✖️512 resolution.

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Kangjie Chen, Minghan Qin, Yu Li†, Haoqian Wang†

• With monocular video input, HRAvatar reconstructs a high-quality, animatable 3D head avatar that enables realistic relighting effects and simple material editing.

Animatable 3d gaussian: Fast and high-quality reconstruction of multiple human avatars

Yang Liu, Xiang Huang, Minghan Qin, Qinwei Lin, Haoqian Wang (* indicates equal contribution)

• We propose Animatable 3D Gaussian, a novel neural representation for fast and high-fidelity reconstruction of multiple animatable human avatars, which can animate and render the model at interactive rate.

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Minghan Qin*, Yifan Liu*, Yuelang Xu, Xiaochen Zhao, Yebin Liu†, Haoqian Wang†

- We introduce a novel Spatially-Varying Expression (SVE) conditioning, encompassing both spatial positional features and global expression information.

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting

Kangjie Chen, Yingji Zhong, Zhihao Li, Jiaqi Lin, Youyu Chen, Minghan Qin, Haoqian Wang†

• This paper introduces the concept of co-adaptation in 3D Gaussian Splatting, analyzes its impact on rendering artifacts, and proposes strategies (Dropout Regularization & Opacity Noise Injection) to reduce it.

HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

Yuanhao Cai , Zihao Xiao, Yixun Liang, Minghan Qin, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille

• This paper presents HDR-GS, a novel 3D Gaussian splatting-based method for high dynamic range imaging that achieves 1000x speedup over existing methods.

Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections

Dongbin Zhang*, Chuming Wang*, Weitao Wang, Peihao Li, Minghan Qin, Haoqian Wang†

• We utilize 3D Gaussian Splatting with introduced separated intrinsic and dynamic appearance to reconstruct scenes from uncontrolled images, achieving high-quality results and a 1000 × rendering speed increase.

Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images

Chuanrui Zhang*, Yonggen Ling*†, Minglei Lu, Minghan Qin, Haoqian Wang†

• We present CODERS, a one-stage approach for Category-level Object Detection, pose Estimation and Reconstruction from Stereo images.