Lune

ICLR2025Top-tier venue

Reveal Object in Lensless Photography via Region Gaze and Amplification

Xiangjun Yin, Huihui Yue

Abstract

Detecting concealed objects, such as in vivo lesions or camouflage, requires customized imaging systems. Lensless cameras, being compact and flexible, offer a promising alternative to bulky lens systems. However, the absence of lenses leads to measurements lacking visual semantics, posing significant challenges for concealed object detection (COD). To tackle this issue, we propose a region gaze-amplification network (RGANet) for progressively exploiting concealed objects from lensless imaging measurements. Specifically, a region gaze module (RGM) is proposed to mine spatial-frequency cues informed by biological and psychological mechanisms, and a region amplifier (RA) is designed to amplify the details of object regions to enhance COD performance. Furthermore, we contribute the first relevant dataset as a benchmark to prosper the lensless imaging community. Extensive experiments demonstrate the exciting performance of our method. Our codes will be released at https://github.com/YXJ-NTU/ Lensless-COD.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Frequency Perception Network for Camouflaged Object Detection cites Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
  • Frequency Perception Network for Camouflaged Object Detection cites Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on10

  1. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsWenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan et al.ICCV 2021 · 4,909 citations
  2. Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object DetectionYouwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang et al.CVPR 2022 · 417 citations
  3. Frequency Perception Network for Camouflaged Object DetectionRunmin Cong, Mengyao Sun, Sanyi Zhang, Xiaofei Zhou et al.ACM MM 2023 · 130 citations
  4. Domain Generalization via Frequency-domain-based Feature Disentanglement and InteractionJingye Wang, Ruoyi Du, Dongliang Chang, Kongming Liang et al.ACM MM 2022 · 66 citations
  5. DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency DomainYuxi Mi, Yuge Huang, Jiazhen Ji, Hongquan Liu et al.ACM MM 2022 · 34 citations

Related papers

  1. A Simple Framework for 3D Lensless Imaging with Programmable MasksYucheng Zheng, Yi Hua, Aswin C. Sankaranarayanan, M. Salman AsifICCV 2021 · 14 citations
  2. MiNet: Weakly-Supervised Camouflaged Object Detection through Mutual Interaction between Region and Edge CuesYuzhen Niu, Lifen Yang, Rui Xu, Yuezhou Li et al.ACM MM 2024 · 14 citations
  3. Towards Photorealistic Reconstruction of Highly Multiplexed Lensless ImagesSalman Siddique Khan, Adarsh V. R, Vivek Boominathan, Jasper Tan et al.ICCV 2019 · 34 citations
  4. Depth-Aware Concealed Crop Detection in Dense Agricultural ScenesLiqiong Wang, Jinyu Yang, Yanfu Zhang, Fangyi Wang et al.CVPR 2024 · 66 citations
  5. Detecting Camouflaged Object in Frequency DomainYijie Zhong, Bo Li, Lv Tang, Senyun Kuang et al.CVPR 2022 · 271 citations
Dusk over the sea between two cliffs drawn in fine vertical lines