Search Results for author: Yao Gao

Found 11 papers, 3 papers with code

Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions

1 code implementation15 Sep 2024 Xiaolong Qian, Qi Jiang, Yao Gao, Shaohua Gao, Zhonghua Yi, Lei Sun, Kai Wei, Haifeng Li, Kailun Yang, Kaiwei Wang, Jian Bai

A Depth-aware Controllable DoF Imaging (DCDI) framework is proposed equipped with All-in-Focus (AiF) aberration correction and monocular depth estimation, where the recovered image and corresponding depth map are utilized to produce imaging results under diverse DoFs of any high-end lens via patch-wise convolution.

Monocular Depth Estimation

A Flexible Framework for Universal Computational Aberration Correction via Automatic Lens Library Generation and Domain Adaptation

no code implementations9 Sep 2024 Qi Jiang, Yao Gao, Shaohua Gao, Zhonghua Yi, Lei Sun, Hao Shi, Kailun Yang, Kaiwei Wang, Jian Bai

OmniLens extends the idea of universal CAC to a broader concept, where a base model is trained for three cases, including zero-shot CAC with the pre-trained model, few-shot CAC with a little lens-specific data for fine-tuning, and domain adaptive CAC using domain adaptation for lens-descriptions-unknown lens.

Domain Adaptation

A Crowding Distance That Provably Solves the Difficulties of the NSGA-II in Many-Objective Optimization

no code implementations25 Jul 2024 Weijie Zheng, Yao Gao, Benjamin Doerr

These results suggest that our truthful version of the NSGA-II has the same good performance as the classic NSGA-II in two objectives, but can resolve the drastic problems in more than two objectives.

Global Search Optics: Automatically Exploring Optimal Solutions to Compact Computational Imaging Systems

no code implementations30 Apr 2024 Yao Gao, Qi Jiang, Shaohua Gao, Lei Sun, Kailun Yang, Kaiwei Wang

In this work, we present Global Search Optics (GSO) to automatically design compact computational imaging systems through two parts: (i) Fused Optimization Method for Automatic Optical Design (OptiFusion), which searches for diverse initial optical systems under certain design specifications; and (ii) Efficient Physic-aware Joint Optimization (EPJO), which conducts parallel joint optimization of initial optical systems and image reconstruction networks with the consideration of physical constraints, culminating in the selection of the optimal solution.

Image Reconstruction

Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization

1 code implementation15 Mar 2024 Qi Jiang, Zhonghua Yi, Shaohua Gao, Yao Gao, Xiaolong Qian, Hao Shi, Lei Sun, JinXing Niu, Kaiwei Wang, Kailun Yang, Jian Bai

Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications.

Quantization Unsupervised Domain Adaptation

Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers

1 code implementation22 Jun 2023 Qi Jiang, Shaohua Gao, Yao Gao, Kailun Yang, Zhonghua Yi, Hao Shi, Lei Sun, Kaiwei Wang

In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging.

Super-Resolution

Mode-locking Theory for Long-Range Interaction in Artificial Neural Networks

no code implementations10 Mar 2023 Xiuxiu Bai, Shuaishuai Zhao, Yao Gao, Zhe Liu

We verify this theory through simulation experiments and demonstrate the mode-locking pattern in real-world scene models.

Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks

no code implementations20 May 2022 Xiuxiu Bai, Zhe Liu, Yao Gao, Bin Liu, Yongqiang Hao

Artificial neural networks have realized incredible successes at image recognition, but the underlying mechanism of visual space representation remains a huge mystery.

Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift

no code implementations23 Jul 2021 Pinzhuo Tian, Yao Gao

However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to generalize to tasks from the other unseen domains.

Cross-Domain Few-Shot Domain Generalization +1

Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation

no code implementations21 Apr 2021 Zhong-Qiu Zhao, Yao Gao, Yuchen Ge, Weidong Tian

Experimental results on COCO and OCHuman keypoints datasets show that our proposed ODKD can improve the performance of different lightweight models by a large margin, and HRNet-W16 equipped with ODKD achieves state-of-the-art performance for lightweight human pose estimation.

Binarization Knowledge Distillation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.