7 papers · 1 filter
DR-GS: Physically-Based Deformable and Relightable 2D Gaussians
Jiaxin Li, Tong Wu, Yi Wei +2
Gaussian splatting (GS) has garnered significant attention in VR/AR and digital content creation due to its explicit parameterization and efficient rendering capabilities. However,…
PISE: Physics-Anchored Semantically-Enhanced Deep Computational Ghost Imaging for Robust Low-Bandwidth Machine Perception
Tong Wu
We propose PISE, a physics-informed deep ghost imaging framework for low-bandwidth edge perception. By combining adjoint operator initialization with semantic guidance, PISE improv…
ROSGS: Relightable Outdoor Scenes With Gaussian Splatting
Lianjun Liao, Chunhui Zhang, Tong Wu +3
Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and…
Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions
Sijia Jiang, Tong Wu, Jing Hua +1
It is vital to recover 3D geometry from multi-view RGB images in many 3D computer vision tasks. The latest methods infer the geometry represented as a signed distance field by mini…
DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shading
Tong Wu, Jia-Mu Sun, Yu-Kun Lai +3
Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstructi…
Recent Advances in 3D Gaussian Splatting
Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang +4
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Field…
Retargeting Visual Data with Deformation Fields
Tim Elsner, Julia Berger, Tong Wu +3
Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programm…