DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis

• URL: http://arxiv.org/abs/2603.23924v1
• Date: Wed, 25 Mar 2026 04:28:17 GMT
• Title: DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis
• Abstract summary: We propose DepthArb, a training-free framework that resolves occlusion ambiguities by arbitrating attention competition between interacting objects.<n>We show that DepthArb consistently outperforms state-of-the-art baselines in synthesizing both occlusion accuracy and visual fidelity.<n>As a plug-and-play method, DepthArb seamlessly enhances the compositional capabilities of diffusion backbones.
• Score: 21.345962204165932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image diffusion models frequently exhibit deficiencies in synthesizing accurate occlusion relationships of multiple objects, particularly within dense overlapping regions. Existing training-free layout-guided methods predominantly rely on rigid spatial priors that remain agnostic to depth order, often resulting in concept mixing or illogical occlusion. To address these limitations, we propose DepthArb, a training-free framework that resolves occlusion ambiguities by arbitrating attention competition between interacting objects. Specifically, DepthArb employs two core mechanisms: Attention Arbitration Modulation (AAM), which enforces depth-ordered visibility by suppressing background activations in overlapping regions, and Spatial Compactness Control (SCC), which preserves structural integrity by curbing attention divergence. These mechanisms enable robust occlusion generation without model retraining. To systematically evaluate this capability, we propose OcclBench, a comprehensive benchmark designed to evaluate diverse occlusion scenarios. Extensive evaluations demonstrate that DepthArb consistently outperforms state-of-the-art baselines in both occlusion accuracy and visual fidelity. As a plug-and-play method, DepthArb seamlessly enhances the compositional capabilities of diffusion backbones, offering a novel perspective on spatial layering within generative models.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets [43.71958109614362]
  Closely-Spaced Infrared Small Targets (CSIST) typically exhibit energy overlap, manifesting as indistinguishable blobs in infrared images.<n>This ambiguity invalidates the one-to-one mapping assumption of traditional detection.<n>We propose a one-stage lightweight paradigm which demonstrates that deep unfolding is not necessary.
  arXiv  Detail & Related papers  (2026-07-17T14:42:51Z)
• OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation [49.49933361280724]
  We introduce OcclusionFormer, a novel framework that explicitly models Z-order priority by decoupling instances.<n>We also introduce a queried alignment loss that explicitly supervises individual instances and enhances semantic consistency.<n>The proposed method effectively reduces ambiguity in overlapping regions, enforces correct occlusion dependencies, and preserves structural integrity, leading to substantial accuracy gains across diverse scenes.
  arXiv  Detail & Related papers  (2026-05-20T16:10:44Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery [12.116457701406047]
  Multi-person 3D reconstruction is pivotal for real-world interaction analysis.<n>Current approaches rely on single-modality inputs, which inherently lack geometric guidance.<n>We propose Contrastive Multi-modal Hypergraph Reasoning to synergize semantic, geometric, and pose cues for crowd reconstruction.
  arXiv  Detail & Related papers  (2026-04-01T09:39:01Z)
• Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning [3.4174356345935393]
  We propose MoDOT, a novel method that jointly estimates depth and OBs from a single image.<n>MoDOT incorporates a new module, CASM, which combines cross-attention and multi-scale strip convolutions to leverage mid-level OB features.<n>Experiments demonstrate the mutual benefits of jointly estimating depth and OBs, and validate the effectiveness of MoDOT's design.
  arXiv  Detail & Related papers  (2025-05-27T14:15:19Z)
• Learning to Align and Refine: A Foundation-to-Diffusion Framework for Occlusion-Robust Two-Hand Reconstruction [50.952228546326516]
  Two-hand reconstruction from monocular images faces persistent challenges due to complex and dynamic hand postures.<n>Existing approaches struggle with such alignment issues, often resulting in misalignment and penetration artifacts.<n>We propose a dual-stage Foundation-to-Diffusion framework that precisely align 2D prior guidance from vision foundation models.
  arXiv  Detail & Related papers  (2025-03-22T14:42:27Z)
• High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy [23.431898388115044]
  High-precision dichotomous image segmentation (DIS) is a task of extracting fine-grained objects from high-resolution images.<n>Existing methods face a dilemma: non-diffusion methods work efficiently but suffer from false or missed detections due to weak semantics.<n>We find pseudo depth information from monocular depth estimation models can provide essential semantic understanding.
  arXiv  Detail & Related papers  (2025-03-08T07:02:28Z)
• Unsupervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion [27.677765887774186]
  Unsupervised monocular depth estimation has received widespread attention because of its capability to train without ground truth.<n>We employ a well-converging diffusion model among generative networks for unsupervised monocular depth estimation.<n>This model significantly enriches the model's capacity for learning and interpreting depth distribution.
  arXiv  Detail & Related papers  (2024-06-14T07:31:20Z)
• DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery [71.6345505427213]
  DPMesh is an innovative framework for occluded human mesh recovery. It capitalizes on the profound diffusion prior about object structure and spatial relationships embedded in a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-04-01T18:59:13Z)
• Depth-aware Volume Attention for Texture-less Stereo Matching [67.46404479356896]
  We propose a lightweight volume refinement scheme to tackle the texture deterioration in practical outdoor scenarios. We introduce a depth volume supervised by the ground-truth depth map, capturing the relative hierarchy of image texture. Local fine structure and context are emphasized to mitigate ambiguity and redundancy during volume aggregation.
  arXiv  Detail & Related papers  (2024-02-14T04:07:44Z)
• Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space [7.021872917042116]
  We introduce the Occlusion Sensitivity Analysis with Deep Feature Augmentation Subspace (OSA-DAS), a novel perturbation-based interpretability approach for computer vision. Our method utilizes the output vector of a DNN to build low-dimensional subspaces within the deep feature vector space, offering a more precise explanation of the model prediction. We test extensively on the ImageNet-1k, and our class- and model-agnostic approach outperforms commonly used interpreters.
  arXiv  Detail & Related papers  (2023-11-25T13:26:40Z)
• Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification [36.86516784815214]
  We propose a transformer-based Attention Disturbance and Dual-Path Constraint Network (ADP) to enhance the generalization of attention networks. To imitate real-world obstacles, we introduce an Attention Disturbance Mask (ADM) module that generates an offensive noise. We also develop a Dual-Path Constraint Module (DPC) that can obtain preferable supervision information from holistic images.
  arXiv  Detail & Related papers  (2023-03-20T09:56:35Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)

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.