pith. sign in

arxiv: 2605.14552 · v3 · pith:QDILO2T6new · submitted 2026-05-14 · 💻 cs.CV

LiWi: Layering in the Wild

Yu He , Fang Li , Haoyang Tong , Lichen Ma , Xinyuan Shan , Jingling Fu , Dong Chen , Luohang Liu
show 2 more authors
Junshi Huang Yan Li
This is my paper

Pith reviewed 2026-06-30 21:39 UTC · model grok-4.3

classification 💻 cs.CV
keywords natural image decompositionlayered image generationagent-driven data decompositionshadow-guided learningdegradation-restorationin-the-wild imagesimage editingdataset construction
0
0 comments X

The pith

An agent-orchestrated pipeline generates a 100k-image dataset of layered natural photos and trains a model that outperforms priors on decomposition metrics.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to establish a scalable method for decomposing in-the-wild images into editable layers, a task previously limited to graphic design because of data scarcity and difficulties modeling illumination and boundaries. It introduces an Agent-driven Data Decomposition pipeline that uses agents and tools to synthesize over 100,000 layered images without manual labeling, producing the LiWi-100k dataset. A joint model is then trained with shadow-guided learning to capture illumination effects and a degradation-restoration objective to refine alpha boundaries. If the approach holds, natural images become editable at the layer level with higher photometric and boundary fidelity than before. Readers would care because this removes a key barrier to practical applications like fine-grained photo editing.

Core claim

The paper claims that orchestrating agents to synthesize the LiWi-100k dataset, followed by training with shadow-guided learning to model illumination and degradation-restoration to supervise boundaries, produces a decomposition framework that achieves state-of-the-art results on natural images, beating existing models on RGB L1 error and Alpha IoU.

What carries the argument

The Agent-driven Data Decomposition (ADD) pipeline that synthesizes layered data without manual intervention, paired with shadow-guided learning and degradation-restoration objective for photometric and boundary accuracy.

If this is right

  • Layered data for natural images can be generated at large scale without human annotation.
  • Illumination effects receive explicit supervision during training.
  • Alpha boundaries receive targeted correction through the restoration task.
  • The resulting decompositions support finer editing operations on real photographs than prior methods.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The agent orchestration could be reused to synthesize training data for related tasks such as shadow removal or instance matting.
  • Adding temporal consistency terms might allow the same pipeline to produce layered video.
  • If the generated data distribution matches real images closely, the model might transfer to downstream applications like compositing or relighting.

Load-bearing premise

The ADD pipeline produces high-quality layered data that faithfully captures real-world illumination effects and structural boundaries without manual intervention or domain shift issues.

What would settle it

Evaluating the trained model on a collection of real natural images paired with independent human-annotated layers and finding that RGB L1 and Alpha IoU scores do not exceed current baselines.

Figures

Figures reproduced from arXiv: 2605.14552 by Dong Chen, Fang Li, Haoyang Tong, Jingling Fu, Junshi Huang, Lichen Ma, Luohang Liu, Xinyuan Shan, Yan Li, Yu He.

Figure 1
Figure 1. Figure 1: Overview of our ADD pipeline. The system leverages agent and specialized tools to [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of pass and fail examples from [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of pass and fail examples from [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Data distribution and samples of LiWi-100k. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Effect of the shadow layer. The shadow layer records foreground-related lighting changes, [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustration of the restora￾tion process from degraded regions to the natural image manifold. 4.2 Degraded Boundary Refinement In the layer generation task, given the ground-truth image x0 ∈ {S} ∪ B ∪ F, the flow-matching [33] method constructs a linear path that transports a Gaussian sample ϵ to image x0. The latent represen￾tation at time step t ∈ [0, 1] is defined via linear interpolation: zt = (1 − t)ϵ… view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative comparison on in-the-wild layer decomposition. [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative comparison on in-the-wild layer decomposition. [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Layer decomposition guided by visual prompt. [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: The degraded layer is obtained by expanding the original image region and then applying [PITH_FULL_IMAGE:figures/full_fig_p014_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Results of LiWi framework on the test set of LiWi-100k. For various natural scenes [PITH_FULL_IMAGE:figures/full_fig_p015_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Visualization of the Liwi dataset with 2 and 3 layers. As shown, in diverse scenes, our [PITH_FULL_IMAGE:figures/full_fig_p016_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Visualization of the LiWi-100k dataset across multiple layers and aspect ratios. As the [PITH_FULL_IMAGE:figures/full_fig_p017_12.png] view at source ↗
read the original abstract

Recent advances in generative models have empowered impressive layered image generation, yet their success is largely confined to graphic design domains. The layering of in-the-wild images remains an underexplored problem, limiting fine-grained editing and applications of images in real-world scenarios. Specifically, challenges remain in scalable layered data and the modeling of object interaction in natural images, such as illumination effects and structural boundary. To address these bottlenecks, we propose a novel framework for high-fidelity natural image decomposition. First, we introduce an Agent-driven Data Decomposition (ADD) pipeline that orchestrates agents and tools to synthesize layered data without manual intervention. Utilizing this pipeline, we construct a large-scale dataset, named LiWi-100k, with over 100,000 high-quality layered in-the-wild images. Second, we present a novel framework that jointly improves photometric fidelity and alpha boundary accuracy. Specifically, shadow-guided learning explicitly models the illumination effects, and degradation-restoration objective provides boundary-correction supervision by recovering clean foreground image from degraded one. Extensive experiments demonstrate that our framework achieves state-of-the-art (SoTA) performance in natural image decomposition, outperforming existing models in RGB L1 and Alpha IoU metrics. We will soon release our code and dataset.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper claims to solve natural image layering by introducing an Agent-driven Data Decomposition (ADD) pipeline that synthesizes the LiWi-100k dataset of >100k layered in-the-wild images without manual annotation. It then trains a model using shadow-guided learning to capture illumination effects and a degradation-restoration objective to improve alpha boundaries, reporting state-of-the-art RGB L1 and Alpha IoU performance over prior methods.

Significance. If the ADD pipeline's outputs are shown to faithfully reproduce real-world illumination and boundary statistics, the work would supply both a scalable data source and a training recipe that directly targets photometric and structural fidelity, potentially enabling more reliable fine-grained editing of natural photographs. Releasing the dataset and code would further amplify impact.

major comments (1)
  1. [§3.1] §3.1 (ADD pipeline): The central claim that the framework achieves SoTA performance rests on the assumption that ADD-generated layers match real illumination effects and structural boundaries. No quantitative validation (e.g., comparison of shadow placement, edge alignment, or photometric statistics against human-annotated or captured real layers) is described; without it, the shadow-guided loss and degradation-restoration objective may optimize to synthetic artifacts rather than natural-image distributions, rendering the reported RGB L1 / Alpha IoU gains non-generalizable.
minor comments (1)
  1. [Abstract] Abstract: the statement 'We will soon release our code and dataset' should include a concrete timeline or repository link to allow reproducibility assessment.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on the ADD pipeline validation. We address the major comment below and will incorporate additional analysis in the revision.

read point-by-point responses

  1. Referee: [§3.1] §3.1 (ADD pipeline): The central claim that the framework achieves SoTA performance rests on the assumption that ADD-generated layers match real illumination effects and structural boundaries. No quantitative validation (e.g., comparison of shadow placement, edge alignment, or photometric statistics against human-annotated or captured real layers) is described; without it, the shadow-guided loss and degradation-restoration objective may optimize to synthetic artifacts rather than natural-image distributions, rendering the reported RGB L1 / Alpha IoU gains non-generalizable.

    Authors: We agree that the current manuscript does not include direct quantitative comparisons of illumination statistics, shadow placement, or boundary properties between ADD-generated layers and real human-annotated layers. The reported SoTA results are measured on real test images using RGB L1 and Alpha IoU, providing indirect evidence of generalization. To strengthen the claims, we will add a dedicated analysis (new subsection or appendix) that computes and compares photometric histograms, shadow intensity distributions, and edge alignment metrics against available real layered data. This will be included in the revised version. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical pipeline and training rest on independent data synthesis and evaluation

full rationale

The paper introduces an ADD pipeline for dataset creation (LiWi-100k) and a model trained with shadow-guided and degradation-restoration losses, claiming SoTA on RGB L1 and Alpha IoU. No equations, derivations, or first-principles predictions are present that reduce to fitted parameters or self-citations by construction. The central claims are experimental outcomes from training on synthesized data and testing on held-out metrics, which are independent of the method's internal definitions. No load-bearing self-citation chains or ansatzes imported from prior author work are described in the provided text.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based on abstract only; no explicit free parameters, axioms, or invented entities are described. The ADD pipeline and shadow-guided learning are presented as novel techniques rather than new physical entities.

pith-pipeline@v0.9.1-grok · 5772 in / 1002 out tokens · 32536 ms · 2026-06-30T21:39:11.140906+00:00 · methodology

Review history (3 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

41 extracted references · 15 canonical work pages · 6 internal anchors

  1. [1]

    Layered neural atlases for consistent video editing.ACM Transactions on Graphics, 40(6):1–12, 2021

    Yoni Kasten, Dolev Ofri, Oliver Wang, and Tali Dekel. Layered neural atlases for consistent video editing.ACM Transactions on Graphics, 40(6):1–12, 2021

    2021

  2. [2]

    Text2live: Text-driven layered image and video editing

    Omer Bar-Tal, Dolev Ofri-Amar, Rafail Fridman, Yoni Kasten, and Tali Dekel. Text2live: Text-driven layered image and video editing. InEuropean Conference on Computer Vision, pages 707–723, 2022

    2022

  3. [3]

    Shape- aware text-driven layered video editing

    Yao-Chih Lee, Ji-Ze Genevieve Jang, Yi-Ting Chen, Elizabeth Qiu, and Jia-Bin Huang. Shape- aware text-driven layered video editing. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14317–14326, 2023

    2023

  4. [4]

    Resolution-robust large mask inpainting with fourier convolutions

    Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, Anastasia Remizova, Arsenii Ashukha, Aleksei Silvestrov, Naejin Kong, Harshith Goka, Kiwoong Park, and Victor Lempitsky. Resolution-robust large mask inpainting with fourier convolutions. InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2149–2159, 2022

    2022

  5. [5]

    Layerd: Decomposing raster graphic designs into layers

    Tomoyuki Suzuki, Kang-Jun Liu, Naoto Inoue, and Kota Yamaguchi. Layerd: Decomposing raster graphic designs into layers. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 17783–17792, 2025

    2025

  6. [6]

    Qwen-image-layered: Towards inherent editability via layer decomposition.arXiv preprint arXiv:2512.15603, 2025

    Shengming Yin, Zekai Zhang, Zecheng Tang, Kaiyuan Gao, Xiao Xu, Kun Yan, Jiahao Li, Yilei Chen, Yuxiang Chen, Heung-Yeung Shum, et al. Qwen-image-layered: Towards inherent editability via layer decomposition.arXiv preprint arXiv:2512.15603, 2025

    work page arXiv 2025

  7. [7]

    Omnipsd: Layered psd generation with diffusion transformer.arXiv preprint arXiv:2512.09247, 2025

    Cheng Liu, Yiren Song, Haofan Wang, and Mike Zheng Shou. Omnipsd: Layered psd generation with diffusion transformer.arXiv preprint arXiv:2512.09247, 2025

    work page arXiv 2025

  8. [8]

    A survey on intrinsic images: Delving deep into lambert and beyond.International Journal of Computer Vision, 130:836–868, 2022

    Elena Garces, Carlos Rodriguez-Pardo, Dan Casas, and Jorge Lopez-Moreno. A survey on intrinsic images: Delving deep into lambert and beyond.International Journal of Computer Vision, 130:836–868, 2022

    2022

  9. [9]

    Canvasvae: Learning to generate vector graphic documents

    Kota Yamaguchi. Canvasvae: Learning to generate vector graphic documents. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5481–5489, 2021

    2021

  10. [10]

    Deepprimitive: Image decomposition by layered primitive detection

    Jiahui Huang, Jun Gao, Vignesh Ganapathi-Subramanian, Hao Su, Yin Liu, Chengcheng Tang, and Leonidas J Guibas. Deepprimitive: Image decomposition by layered primitive detection. Computational Visual Media, 4(4):385–397, 2018

    2018

  11. [11]

    Generative image layer decomposition with visual effects

    Jinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim, Daniil Pakhomov, Mengwei Ren, Jianming Zhang, Zhe Lin, Cihang Xie, and Yuyin Zhou. Generative image layer decomposition with visual effects. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7643–7653, 2025

    2025

  12. [12]

    Text2layer: Layered image generation using latent diffusion model.arXiv preprint arXiv:2307.09781, 2023

    Xinyang Zhang, Wentian Zhao, Xin Lu, and Jeff Chien. Text2layer: Layered image generation using latent diffusion model.arXiv preprint arXiv:2307.09781, 2023. 10

    work page arXiv 2023

  13. [13]

    Layerdiff: Exploring text-guided multi-layered composable image synthesis via layer-collaborative diffusion model

    Runhui Huang, Kaixin Cai, Jianhua Han, Xiaodan Liang, Renjing Pei, Guansong Lu, Songcen Xu, Wei Zhang, and Hang Xu. Layerdiff: Exploring text-guided multi-layered composable image synthesis via layer-collaborative diffusion model. InEuropean Conference on Computer Vision, pages 144–160. Springer, 2024

    2024

  14. [14]

    Art: Anonymous region transformer for variable multi-layer transparent image generation

    Yifan Pu, Yiming Zhao, Zhicong Tang, Ruihong Yin, Haoxing Ye, Yuhui Yuan, Dong Chen, Jianmin Bao, Sirui Zhang, Yanbin Wang, et al. Art: Anonymous region transformer for variable multi-layer transparent image generation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 7952–7962, 2025

    2025

  15. [15]

    Mulan: A multi layer annotated dataset for controllable text-to-image generation

    Petru-Daniel Tudosiu, Yongxin Yang, Shifeng Zhang, Fei Chen, Steven McDonagh, Gerasimos Lampouras, Ignacio Iacobacci, and Sarah Parisot. Mulan: A multi layer annotated dataset for controllable text-to-image generation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22413–22422, 2024

    2024

  16. [16]

    Qwen-Image Technical Report

    Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, et al. Qwen-image technical report.arXiv preprint arXiv:2508.02324, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  17. [17]

    Rethinking layered graphic design generation with a top-down approach

    Jingye Chen, Zhaowen Wang, Nanxuan Zhao, Li Zhang, Difan Liu, Jimei Yang, and Qifeng Chen. Rethinking layered graphic design generation with a top-down approach. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 16861–16870, 2025

    2025

  18. [18]

    A Unified and Controllable Framework for Layered Image Generation with Visual Effects

    Jinrui Yang, Qing Liu, Yijun Li, Mengwei Ren, Letian Zhang, Zhe Lin, Cihang Xie, and Yuyin Zhou. Controllable layered image generation for real-world editing.arXiv preprint arXiv:2601.15507, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  19. [19]

    Referring layer decomposition.arXiv preprint arXiv:2602.19358, 2026

    Fangyi Chen, Yaojie Shen, Lu Xu, Ye Yuan, Shu Zhang, Yulei Niu, and Longyin Wen. Referring layer decomposition.arXiv preprint arXiv:2602.19358, 2026

    work page arXiv 2026

  20. [20]

    Transparent

    Lvmin Zhang and Maneesh Agrawala. Transparent image layer diffusion using latent trans- parency.arXiv preprint arXiv:2402.17113, 2024

    work page arXiv 2024

  21. [21]

    Dreamlayer: Simultaneous multi-layer generation via diffusion model

    Junjia Huang, Pengxiang Yan, Jinhang Cai, Jiyang Liu, Zhao Wang, Yitong Wang, Xinglong Wu, and Guanbin Li. Dreamlayer: Simultaneous multi-layer generation via diffusion model. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3357–3366, 2025

    2025

  22. [22]

    Psdiffusion: Harmonized multi-layer image generation via layout and appearance alignment

    Dingbang Huang, Wenbo Li, Yifei Zhao, Xinyu Pan, Yanhong Zeng, and Bo Dai. Psdiffusion: Harmonized multi-layer image generation via layout and appearance alignment. InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3233–3242, 2026

    2026

  23. [23]

    Layeringdiff: Layered image synthesis via generation, then disassembly with generative knowledge.arXiv preprint arXiv:2501.01197, 2025

    Kyoungkook Kang, Gyujin Sim, Geonung Kim, Donguk Kim, Seungho Nam, and Sunghyun Cho. Layeringdiff: Layered image synthesis via generation, then disassembly with generative knowledge.arXiv preprint arXiv:2501.01197, 2025

    work page arXiv 2025

  24. [24]

    Layerfusion: Harmonized multi-layer text-to-image generation with generative priors

    Yusuf Dalva, Yijun Li, Qing Liu, Nanxuan Zhao, Jianming Zhang, Zhe Lin, and Pinar Yanardag. Layerfusion: Harmonized multi-layer text-to-image generation with generative priors. In NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI, 2024

    2025

  25. [25]

    From inpainting to layer decomposition: Repurposing generative inpainting models for image layer decomposition.arXiv preprint arXiv:2511.20996, 2025

    Jingxi Chen, Yixiao Zhang, Xiaoye Qian, Zongxia Li, Cornelia Fermuller, Caren Chen, and Yiannis Aloimonos. From inpainting to layer decomposition: Repurposing generative inpainting models for image layer decomposition.arXiv preprint arXiv:2511.20996, 2025

    work page arXiv 2025

  26. [26]

    Datasetagent: A novel multi-agent system for auto-constructing datasets from real-world images

    Haoran Sun, Haoyu Bian, Shaoning Zeng, Yunbo Rao, Xu Xu, Lin Mei, and Jianping Gou. Datasetagent: A novel multi-agent system for auto-constructing datasets from real-world images. arXiv preprint arXiv:2507.08648, 2025

    work page arXiv 2025

  27. [27]

    Qwen3-VL Technical Report

    Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, et al. Qwen3-vl technical report.arXiv preprint arXiv:2511.21631, 2025. 11

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  28. [28]

    Flux.2-klein-9b, 2026

    Black Forest Labs. Flux.2-klein-9b, 2026. URL https://bfl.ai/models/flux-2-klein. Accessed: 2026-04-27

    2026

  29. [29]

    Rmbg-1.4: Background removal model, 2024

    BRIA AI. Rmbg-1.4: Background removal model, 2024. URL https://huggingface.co/ briaai/RMBG-1.4. Accessed: 2026-04-27

    2024

  30. [30]

    Bilateral reference for high-resolution dichotomous image segmentation.CAAI Artificial Intelligence Research, 2024

    Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, and Nicu Sebe. Bilateral reference for high-resolution dichotomous image segmentation.CAAI Artificial Intelligence Research, 2024

    2024

  31. [31]

    Rmbg-2.0: Background removal model, 2024

    BRIA AI. Rmbg-2.0: Background removal model, 2024. URL https://huggingface.co/ briaai/RMBG-2.0. Accessed: 2026-04-27

    2024

  32. [32]

    SAM 3: Segment Anything with Concepts

    Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, et al. Sam 3: Segment anything with concepts.arXiv preprint arXiv:2511.16719, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  33. [33]

    Flow Matching for Generative Modeling

    Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. Flow matching for generative modeling.arXiv preprint arXiv:2210.02747, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  34. [34]

    Adam: A Method for Stochastic Optimization

    Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  35. [35]

    Highly accurate dichotomous image segmentation

    Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, et al. Highly accurate dichotomous image segmentation. 2022

    2022

  36. [36]

    Camouflaged object detection

    Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen, and Ling Shao. Camouflaged object detection. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2777–2787, 2020

    2020

  37. [37]

    U2-net: Going deeper with nested u-structure for salient object detection

    Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R Zaiane, and Martin Jagersand. U2-net: Going deeper with nested u-structure for salient object detection. 106: 107404, 2020

    2020

  38. [38]

    Deep high-resolution representation learning for visual recognition

    Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, et al. Deep high-resolution representation learning for visual recognition. 43(10):3349–3364, 2020

    2020

  39. [39]

    Pyramid grafting network for one-stage high resolution saliency detection

    Chenxi Xie, Changqun Xia, Mingcan Ma, Zhirui Zhao, Xiaowu Chen, and Jia Li. Pyramid grafting network for one-stage high resolution saliency detection. 2022

    2022

  40. [40]

    Dichotomous image segmentation with frequency priors

    Yan Zhou, Bo Dong, Yuanfeng Wu, Wentao Zhu, Geng Chen, and Yanning Zhang. Dichotomous image segmentation with frequency priors. 2023

    2023

  41. [41]

    arXiv preprint arXiv:2401.03407 (2024)

    Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, and Nicu Sebe. Bilateral reference for high-resolution dichotomous image segmentation.arXiv preprint arXiv:2401.03407, 2024. 12 A Complete Zero-Shot Foreground Segmentation Results on Real-World Data We compare our method with various foreground segmentation approaches on the fo...

    work page arXiv 2024