Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models

• URL: http://arxiv.org/abs/2503.18947v1
• Date: Mon, 24 Mar 2025 17:59:56 GMT
• Title: Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models
• Authors: Jae Joong Lee, Bedrich Benes, Raymond A. Yeh,
• Abstract summary: Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object.<n>Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal masks or synthetic training data.<n>This work introduces a tuning-free approach that repurposes pretrained diffusion-based inpainting models for amodal segmentation.
• Score: 16.800402755022482
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object. Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal masks or synthetic training data. Consequently, their performance depends on the quality of the datasets, which often lack diversity and scale. This work introduces a tuning-free approach that repurposes pretrained diffusion-based inpainting models for amodal segmentation. Our approach is motivated by the "occlusion-free bias" of inpainting models, i.e., the inpainted objects tend to be complete objects without occlusions. Specifically, we reconstruct the occluded regions of an object via inpainting and then apply segmentation, all without additional training or fine-tuning. Experiments on five datasets demonstrate the generalizability and robustness of our approach. On average, our approach achieves 5.3% more accurate masks over the state-of-the-art.

Related papers

• Sequential Amodal Segmentation via Cumulative Occlusion Learning [15.729212571002906]
  A visual system must be able to segment both the visible and occluded regions of objects, while discerning their occlusion order. We introduce a diffusion model with cumulative occlusion learning designed for sequential amodal segmentation of objects with uncertain categories. This model iteratively refines the prediction using the cumulative mask strategy during diffusion, effectively capturing the uncertainty of invisible regions. It is akin to the human capability for amodal perception, i.e., to decipher the spatial ordering among objects and accurately predict complete contours for occluded objects in densely layered visual scenes.
  arXiv  Detail & Related papers  (2024-05-09T14:17:26Z)
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [56.71672127740099]
  We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets. We leverage different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets.
  arXiv  Detail & Related papers  (2024-03-29T10:38:25Z)
• pix2gestalt: Amodal Segmentation by Synthesizing Wholes [34.45464291259217]
  pix2gestalt is a framework for zero-shot amodal segmentation. We learn a conditional diffusion model for reconstructing whole objects in challenging zero-shot cases.
  arXiv  Detail & Related papers  (2024-01-25T18:57:36Z)
• Amodal Ground Truth and Completion in the Wild [84.54972153436466]
  We use 3D data to establish an automatic pipeline to determine authentic ground truth amodal masks for partially occluded objects in real images. This pipeline is used to construct an amodal completion evaluation benchmark, MP3D-Amodal, consisting of a variety of object categories and labels.
  arXiv  Detail & Related papers  (2023-12-28T18:59:41Z)
• Denoising Diffusion Semantic Segmentation with Mask Prior Modeling [61.73352242029671]
  We propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a denoising diffusion generative model. We evaluate the proposed prior modeling with several off-the-shelf segmentors, and our experimental results on ADE20K and Cityscapes demonstrate that our approach could achieve competitively quantitative performance.
  arXiv  Detail & Related papers  (2023-06-02T17:47:01Z)
• Learning 3D Photography Videos via Self-supervised Diffusion on Single Images [105.81348348510551]
  3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints. We present a novel task: out-animation, which extends the space and time of input objects.
  arXiv  Detail & Related papers  (2023-02-21T16:18:40Z)
• Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models [6.408114351192012]
  We present a novel method that enables the generation of general foreground-background segmentation models from simple textual descriptions. We show results on the task of segmenting four different objects (humans, dogs, cars, birds) and a use case scenario in medical image analysis.
  arXiv  Detail & Related papers  (2022-12-29T13:51:54Z)
• What You See is What You Classify: Black Box Attributions [61.998683569022006]
  We train a deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum. Unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks. We show that our attributions are superior to established methods both visually and quantitatively.
  arXiv  Detail & Related papers  (2022-05-23T12:30:04Z)
• Unsupervised Object Learning via Common Fate [61.14802390241075]
  Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We decompose this problem into three easier subtasks, and provide candidate solutions for each of them. We show that our approach allows learning generative models that generalize beyond the occlusions present in the input videos.
  arXiv  Detail & Related papers  (2021-10-13T08:22:04Z)
• Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model [19.235173141731885]
  Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. We formulate amodal segmentation as an out-of-task and out-of-distribution generalization problem. Our algorithm outperforms alternative methods that use the same supervision by a large margin.
  arXiv  Detail & Related papers  (2020-10-25T18:01:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.