Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation

• URL: http://arxiv.org/abs/2605.24533v1
• Date: Sat, 23 May 2026 11:53:49 GMT
• Title: Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation
• Abstract summary: Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations.<n>Existing methods acquire shape priors through fixed-capacity encoding spaces or expensive generative models.<n>We propose a gated reliability-adaptive shape prior framework that combines learnable prototypes via cross-attention.
• Score: 0.25489046505746704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations and must be inferred with the aid of shape priors. Existing methods acquire shape priors through fixed-capacity encoding spaces or expensive generative models, and inject them uniformly across all spatial positions without adapting to the varying prior demand between visible and occluded regions. In this paper, we propose a gated reliability-adaptive shape prior framework, which introduces a shape prior memory module that combines learnable prototypes via cross-attention to produce instance-adaptive shape priors through weighted prototype combination rather than generation. A spatial adaptive reliability gate then employs the signed distance field of the visible mask to modulate injection intensity at each position according to its occlusion depth, preserving reliable features in visible regions while directing shape compensation toward occluded areas. Experiments on two mainstream amodal instance segmentation benchmarks demonstrate that the proposed method outperforms existing approaches under multiple evaluation settings, improving the mean intersection-over-union over occluded regions by over 11 percentage points on one of the two benchmarks under the standard setting, while using approximately one-third of the total parameters. Linear probing analysis further reveals that the visible-mask cross-attention module implicitly encodes occlusion geometry into visual token representations, explaining the effectiveness of the proposed module decomposition.

Related papers

• SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching [25.84764820920445]
  We propose SAMatcher, a feature matching framework that formulates correspondence estimation through co-visibility modeling.<n>It introduces a symmetric cross-view interaction mechanism that enables bidirectional feature exchange and cross-view semantic alignment.<n>Our results show that foundation models originally designed for monocular segmentation can be effectively extended to multi-view correspondence reasoning.
  arXiv  Detail & Related papers  (2026-06-02T09:47:59Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• IoUCert: Robustness Verification for Anchor-based Object Detectors [58.35703549470485]
  We introduce IoUCert, a novel formal verification framework designed specifically to overcome these bottlenecks in anchor-based object detection architectures.<n>We show that our method enables the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.
  arXiv  Detail & Related papers  (2026-03-03T14:36:46Z)
• Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation [41.188891367216804]
  Amodal segmentation aims to recover complete object shapes, including occluded regions with no visual appearance.<n>Existing methods rely on strong prompts, such as visible masks or bounding boxes, which are costly or impractical to obtain in real-world settings.<n>We propose VELA, which performs explicit evolution from point-based prompts.
  arXiv  Detail & Related papers  (2025-08-03T08:36:13Z)
• Geometry-Editable and Appearance-Preserving Object Compositon [67.98806888489385]
  General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties.<n>Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation.<n>We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion model that first leverages semantic embeddings to implicitly capture desired geometric transformations.
  arXiv  Detail & Related papers  (2025-05-27T09:05:28Z)
• Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration [44.88739897482003]
  We introduce an innovative paradigm that leverages a diffusion model in matrix space for robust matching matrix estimation.<n>Specifically, we apply the diffusion model in the doubly matrix space for 3D-3D and 2D-3D registration tasks.<n>For all three registration tasks, we provide adaptive matching matrix embedding implementations tailored to the specific characteristics of each task.
  arXiv  Detail & Related papers  (2025-03-06T06:13:27Z)
• MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo [8.303396507129266]
  MSP-MVS is a method introducing multi-granularity segmentation prior to edge-confined patch deformation.<n>We implement equidistribution and disassemble-clustering of correlative reliable pixels.<n>We also introduce disparity-sampling synergistic 3D optimization to help identify global-minimum matching costs.
  arXiv  Detail & Related papers  (2024-07-27T19:00:44Z)
• ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection [114.54835359657707]
  ProposalContrast is an unsupervised point cloud pre-training framework. It learns robust 3D representations by contrasting region proposals. ProposalContrast is verified on various 3D detectors.
  arXiv  Detail & Related papers  (2022-07-26T04:45:49Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Instant recovery of shape from spectrum via latent space connections [33.83258865005668]
  We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the form of a cycle-consistent module to map latent vectors to sequences of eigenvalues. Our data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost.
  arXiv  Detail & Related papers  (2020-03-14T00:48:34Z)

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.