1 citations · 1 across the 3 of their papers we have counts for
5 papers · 1 filter
When Left Is Right? Camera-Motion Understanding beyond Screen
Chong Cheng, Ran Zhang, Xinyuan Li +3
Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet when asked whether the camera moved left or right, most do no be…
Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion
Shuai Li, Jinxu Xiang, Xinyuan Li +5
We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while enabling realistic and physica…
IC-Custom: Diverse Image Customization via In-Context Learning
Yaowei Li, Xiaoyu Li, Zhaoyang Zhang +11
Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventiona…
BiGS: Bidirectional Gaussian Primitives for Relightable 3D Gaussian Splatting
Zhenyuan Liu, Yu Guo, Xinyuan Li +2
We present Bidirectional Gaussian Primitives, an image-based novel view synthesis technique designed to represent and render 3D objects with surface and volumetric materials under…
Textureless Deformable Surface Reconstruction with Invisible Markers
Xinyuan Li, Yu Guo, Yubei Tu +4
Reconstructing and tracking deformable surface with little or no texture has posed long-standing challenges. Fundamentally, the challenges stem from textureless surfaces lacking fe…