activity
20242026
collaborators

10 papers

cs.CV2026

CameraAnything: Refilming Videos with Arbitrary Camera Control

Yixuan Li, Yanhong Zeng, Ka Leong Cheng +11

We introduce CameraAnything, the first unified framework for camera controlled video editing that enables joint control of both intrinsic and extrinsic camera parameters. Existing…

cs.GR2026

EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

Xijie Yang, Mulin Yu, Changjian Jiang +6

Recent radiance-field-based reconstruction methods, such as NeRF and 3DGS, achieve high visual fidelity for indoor scenes, but often break down under scene editing due to baked ill…

cs.CV2026

InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions

Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang +7

End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could…

cs.CV2025

Multi-identity Human Image Animation with Structural Video Diffusion

Zhenzhi Wang, Yixuan Li, Yanhong Zeng +4

Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individ…

cs.CV2025

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Lihan Jiang, Yucheng Mao, Linning Xu +9

We introduce AnySplat, a feed forward network for novel view synthesis from uncalibrated image collections. In contrast to traditional neural rendering pipelines that demand known…

cs.GR2025

Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes

Xijie Yang, Linning Xu, Lihan Jiang +2

3D Gaussian Splatting (3DGS) enables the reconstruction of intricate digital 3D assets from multi-view images by leveraging a set of 3D Gaussian primitives for rendering. Its expli…