In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment

Dongting Hu, Huan Fu, Jiaxian Guo, Liuhua Peng, Tingjin Chu +3 more
2/3/2026

No official code found. Best implementation: timmy11hu/3DOR (2 stars, last commit 2025-11-12).

Semantic Scholar

Code Implementations(1)

timmy11hu/3DORCommunity70%

[NeurIPS 2024] In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment

20C++, CudaJan 3, 202511 months agoNOASSERTION

Cite this paper

@article{hu2026innout,
  title  = {In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment},
  author = {Dongting Hu and Huan Fu and Jiaxian Guo and Liuhua Peng and Tingjin Chu and Feng Liu and Tongliang Liu and Mingming Gong},
  year   = {2026},
  url    = {https://www.semanticscholar.org/paper/eee57b356d24228774785c8bdd44e2bc021fc833},
  journal = {NEURIPS 2024 2024}
}

Discussion