image-to-3d attribute transfer 1neural adjoint networks 1partial correspondence 1self-supervised registration 1spectral methods 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer
Jing Li, Yawei Luo, Xiangze Meng +3
RealSkin is a self‑supervised framework that transfers visual attributes from real photos onto synthetic 3D models by learning correspondences in a spectral domain and refining the…
cs.CV2025
ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation
Jinsheng Quan, Qiaowei Miao, Yichao Xu +5
The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D rec…
cs.CV2025
HarmonPaint: Harmonized Training-Free Diffusion Inpainting
Ying Li, Xinzhe Li, Yong Du +3
Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and sty…