SOURCE-LINKED INTELLIGENCE

PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

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 an

Read original source ↗ Open in workspace

recordType

paper

region

Global