4 papers
Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision
Zhenxiao Liang, Qixing Huang
Editing animatable human avatars typically relies on sparse supervision, often a few edited keyframes, yet naively fitting a reconstructed avatar to these edits frequently causes i…
ShapeGaussian: High-Fidelity 4D Human Reconstruction in Monocular Videos via Vision Priors
Zhenxiao Liang, Ning Zhang, Youbao Tang +4
We introduce ShapeGaussian, a high-fidelity, template-free method for 4D human reconstruction from casual monocular videos. Generic reconstruction methods lacking robust vision pri…
Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method
Yan Zheng, Zhenxiao Liang, Xiaoyan Cong +4
We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-poin…
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Chen Song, Zhenxiao Liang, Bo Sun +1
We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are…