CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding

no code implementations • 22 Apr 2024 • Guibiao Liao, Jiankun Li, Zhenyu Bao, Xiaoqing Ye, Jingdong Wang, Qing Li, Kanglin Liu

Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.

Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching

no code implementations • ICCV 2023 • Junpeng Jing, Jiankun Li, Pengfei Xiong, Jiangyu Liu, Shuaicheng Liu, Yichen Guo, Xin Deng, Mai Xu, Lai Jiang, Leonid Sigal

A novel Uncertainty Guided Adaptive Correlation (UGAC) module is introduced to robustly adapt the same model for different scenarios.

Stereo Matching

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

1 code implementation • CVPR 2022 • Zihua Zheng, Ni Nie, Zhi Ling, Pengfei Xiong, Jiangyu Liu, Hao Wang, Jiankun Li

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow.

Optical Flow Estimation Vocal Bursts Intensity Prediction

Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation

3 code implementations • CVPR 2022 • Jiankun Li, Peisen Wang, Pengfei Xiong, Tao Cai, Ziwei Yan, Lei Yang, Jiangyu Liu, Haoqiang Fan, Shuaicheng Liu

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress.

Stereo Matching