Metraipolis › archive › dc_8cb828ccb978
PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance — arXiv:2609.00956
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00956
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:42.913Z
- SHA-256 of the archived text
9547f60ea7a84d38b601cc60165731b0b2bcc0c3629ddbff562dba2252e0372c- Stable URL of this page
https://metraipolis.com/documento/dc_8cb828ccb978
How to cite
PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance — arXiv:2609.00956 — arXiv (en), https://arxiv.org/abs/2609.00956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cb828ccb978 (Metraipolis archive dc_8cb828ccb978, sha256 9547f60ea7a84d38b601cc60165731b0b2bcc0c3629ddbff562dba2252e0372c)
BibTeX
@misc{dc8cb828ccb978,
title = {PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance — arXiv:2609.00956},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00956},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cb828ccb978; sha256 9547f60ea7a84d38b601cc60165731b0b2bcc0c3629ddbff562dba2252e0372c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Removing an object is not the same as filling its mask. Cast shadows and contact shading usually lie outside the user-provided instance mask M_obj, so a frozen Fill model that edits only that mask leaves the object's photometric footprint on nearby surfaces. Supervised removers learn this joint erasure from paired clean plates. Training-free editors freeze pretrained weights, yet most still treat M_obj as the entire editable support and steer sampling with CLIP or DINO energies that do not predict the occluded scene. We present PredErase, a training-free inference procedure on frozen FLUX.2 and I-JEPA. The method separates where Fill may rewrite pixels from what structure should occupy the hole. A contact-band expansion M_flux of M_obj exposes local residuals on the supporting plane. I-JEPA, pretrained for masked token prediction, supplies a context-conditioned hole target in representation space; sparse projected gradients align decoded Fill completions with that target inside the instance, while coordinates outside the packed support stay locked. Under instance-only masks on RemovalBench, RORD-Val, and DEFACTO-Val, PredErase improves the native FLUX.2 backbone. Supervised removers remain stronger on several full-image appearance metrics; the supported claim is training-free object-and-effect editing of frozen Fill, not replacement of paired-data erasers. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.00956 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:00:58.949Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).