Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses
Hao Liang, Zhixuan Ge, Soumendu Majee +4
We present FastAvatar, a fast and robust algorithm for single-image 3D face reconstruction using 3D Gaussian Splatting (3DGS). Given a single input image from an arbitrary pose, Fa…
cs.CV2025
ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents
Hao Liang, Zhipeng Dong, Kaixin Chen +4
Surround-view perception has garnered significant attention for its ability to enhance the perception capabilities of autonomous driving vehicles through the exchange of informatio…