arXiv:2606. 17584v1 Announce Type: cross Abstract: Finding the initial noise that generates a given data sample, known as inversion, is a key component for downstream applications such as training-free image editing.
By Semin Kim, Jihwan Yoon, Seunghoon Hong
arXiv:2605. 16399v2 Announce Type: replace-cross Abstract: The inversion of diffusion models plays a central role in image editing.
By Barbora Barancikova, Daniil Shmelev, Cristopher Salvi
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support.
arXiv:2602. 10099v2 Announce Type: replace Abstract: Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis.
By Amandeep Kumar, Vishal M. Patel
arXiv:2601. 19180v2 Announce Type: replace-cross Abstract: Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines.
By Lifan Jiang, Boxi Wu, Yuhang Pei, Tianrun Wu, Yongyuan Chen, Yan Zhao, Shiyu Yu, Deng Cai
arXiv:2606. 19802v1 Announce Type: new Abstract: Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.
By Nicolas Zilberstein, Morteza Mardani, Santiago Segarra