Reproduce “POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Wenshuo Chen, Haosen Li, Shaofeng Liang, Lei Wang, Haozhe Jia, Kaishen Yuan, Jieming Wu, Bowen Tian and 1 more
POLARIS adapts classifier-free guidance at each DDIM inversion step to reduce an approximate local noise-error term, using changes in unconditional and prompt-conditioned predictions to choose the scale. It replays that schedule during denoising. On COCO2017 with Stable Diffusion v1.5 at 100 steps, reconstruction PSNR rises from 13.92 to 22.55 dB; this measures fidelity, not semantic edit correctness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.