arXiv Machine Learning
ROCOCO: Robust Outline Completion of Occluded Curvilinear Objects
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 29
OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal
arXiv:2606. 28094v1 Announce Type: cross Abstract: Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the fact that user-provided masks are often inaccurate or incomplete.
arXiv Computer Vision
Sep 2
PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance
PredErase is a training‑free method that removes objects and their photometric effects by guiding a frozen Fill model with predictive latent cues. It expands the user‑provided mask to a contact‑band region, uses I‑JEPA to generate a context‑conditioned target for the hole, and aligns Fill’s completions with this target while keeping surrounding pixels fixed. On benchmarks such as RemovalBench, RORD‑Val, and DEFACTO‑Val, PredErase improves the native FLUX.2 backbone for instance‑only masks, though supervised removers still outperform it on full‑image metrics.
arXiv Machine Learning
3d ago
OccJEPA: Occlusion as Masking for Amodal Video Segmentation
OccJEPA treats occlusion as masking for amodal video segmentation by dropping tokens outside an object's visible mask and using a pre‑trained V‑JEPA 2.1 predictor to fill in the missing features, followed by a lightweight head that decodes these into complete masks. The resulting deterministic model is 33.5× faster than diffusion‑based state‑of‑the‑art methods and achieves higher accuracy on SAIL‑VOS, TAO‑Amodal (including a held‑out test split), and Kubric. Experiments show that the performance gains stem from the predictor’s pre‑trained weights rather than its size, with models ranging from 87 M to 1.85 B parameters.
arXiv AI
Jun 16
Mask Proposal Voting Based on Geodesic Framework for Robust Image Segmentation
arXiv:2606. 14912v1 Announce Type: cross Abstract: Despite great advances, finding accurate segmentation remains a challenging task, especially in scenarios with cluttered backgrounds, complex intensity variations and topology appearance.
arXiv Computer Vision
Oct 9
IS-Diff: Improving Diffusion-Based Inpainting with Better Initial Seed
The paper introduces IS‑Diff, a training‑free diffusion‑based inpainting method that improves semantic consistency by using initial seeds sampled from unmasked regions. It incorporates a dynamic selective refinement mechanism to adjust the initialization strength during intermediate latent stages. Experiments on CelebA‑HQ, ImageNet, and Places2 show that IS‑Diff outperforms state‑of‑the‑art methods across standard and large‑mask inpainting tasks.
arXiv Computer Vision
Sep 3
Structured-Prior-Guided Diffusion Inpainting with Physical Consistency for Traffic Sign Augmentation
The paper introduces a structured‑prior‑guided diffusion inpainting framework that enhances traffic sign augmentation by incorporating semantic, appearance, and geometric priors through text prompts, vector templates, and ControlNet. It enforces physical consistency with colour and edge‑structure losses, achieving superior reconstruction fidelity and OCR accuracy compared to larger models. The synthetic data generated improves detection performance for rare traffic sign classes by up to 7.4× over a real‑data‑only baseline.