📝 Publications

[ICCV 2025] Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
Tianqi Liu*, Zihao Huang*, Zhaoxi Chen, Guangcong Wang, Shoukang Hu, Liao Shen, Huiqiang Sun, Zhiguo Cao, Wei Li, Ziwei Liu.
[Project page] [Paper] [Code] [Video]

Free4D is a tuning-free framework for 4D scene generation from a single image or text.

[ICCV 2025] MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction
Yaopeng Lou, Liao Shen, Tianqi Liu, Jiaqi Li, Zihao Huang, Huiqiang Sun, Zhiguo Cao.
[Paper]

MuGS is the first multi-baseline generalizable gaussian splatting method.

[CVPR 2025] DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting
Liao Shen, Tianqi Liu, Huiqiang Sun, Jiaqi Li, Zhiguo Cao, Wei Li, Chen Change Loy.
[Project page] [Paper] [Code]

We introduce DoF-Gaussian, a controllable depth-of-field method for 3D-GS. We develop a lens-based imaging model based on geometric optics principles to control DoF effects. Our framework is customizable and supports various interactive applications.

[CVPR 2025] WildAvatar: Learning In-the-wild 3D Avatars from the Web
Zihao Huang, Shoukang Hu, Guangcong Wang, Tianqi Liu, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu.
[Project page] [Paper] [Code] [Video]

We present WildAvatar, a web-scale in-the-wild video dataset for 3D avatar creation.

[CVPR 2025 Highlight] CH₃Depth: Efficient and Flexible Depth Foundation Model with Flow Matching
Jiaqi Li, Yiran Wang, Jinghong Zheng, Junrui Zhang, Liao Shen, Tianqi Liu, Zhiguo Cao.
[Paper] [Code]

CH₃Depth is an efficient and flexible flow-matching-based depth estimation framework that achieves state-of-the-art zero-shot performance in accuracy, efficiency, and temporal consistency.

[ECCV 2024] MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu.
[Project page] [Paper] [Code] [Video] [中文解读]

MVSGaussian is a Gaussian-based method designed for efficient reconstruction of unseen scenes from sparse views in a single forward pass. It offers high-quality initialization for fast training and real-time rendering.

[ECCV 2024] DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion
Liao Shen, Tianqi Liu, Huiqiang Sun, Xinyi Ye, Baopu Li, Jianming Zhang, Zhiguo Cao.
[Project page] [Paper] [Code]

By leveraging the prior of diffusion models, DreamMover can generate intermediate images from image pairs with large motion while maintaining semantic consistency.

[CVPR 2024] Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields
Tianqi Liu, Xinyi Ye, Min Shi, Zihao Huang, Zhiyu Pan, Zhan Peng, Zhiguo Cao.
[Project page] [Paper] [Code] [Video]

We present GeFu, a generalizable NeRF method that synthesizes novel views from multi-view images in a single forward pass.

[CVPR 2024] 3D Multi-frame Fusion for Video Stabilization
Zhan Peng, Xinyi Ye, Weiyue Zhao, Tianqi Liu, Huiqiang Sun, Baopu Li, Zhiguo Cao.
[Paper] [Code]

RStab is a novel framework for video stabilization that integrates 3D multi-frame fusion through volume rendering.

[ICCV 2023] When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
Tianqi Liu, Xinyi Ye, Weiyue Zhao, Zhiyu Pan, Min Shi, Zhiguo Cao.
[Paper] [Code]

ETMVSNet uses epipolar geometric priors to constrain feature aggregation fileds, thereby efficiently inferring multi-view depths and reconstructing scenes.

[ICCV 2023] Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Xinyi Ye, Weiyue Zhao, Tianqi Liu, Zihao Huang, Zhiguo Cao, Xin Li.
[Paper] [Code]

DMVSNet proposes a new perspective to consider the depth geometry of multi-view stereo and introduces a dual-depth approach to approximate the depth geometry with saddle-shaped cells.