paper-with-me

Papers

SAIR: Learning Semantic-aware Implicit Representation

2023-10-13 · Canyu Zhang, Xiaoguang Li, Qing Guo, Song Wang

Implicit representation of an image can map arbitrary coordinates in the continuous domain to their corresponding color values, presenting a powerful capability for image reconstruction. Nevertheless, existing implicit representation approaches only focus on building continuous appearance mapping, ignoring the continuities of the semantic information across pixels. As a result, they can hardly achieve desired reconstruction results when the semantic information within input images is corrupted, for example, a large region misses. To address the issue, we propose to learn semantic-aware implicit representation (SAIR), that is, we make the implicit representation of each pixel rely on both its appearance and semantic information (\eg, which object does the pixel belong to). To this end, we propose a framework with two modules: (1) building a semantic implicit representation (SIR) for a corrupted image whose large regions miss. Given an arbitrary coordinate in the continuous domain, we can obtain its respective text-aligned embedding indicating the object the pixel belongs. (2) building an appearance implicit representation (AIR) based on the SIR. Given an arbitrary coordinate in the continuous domain, we can reconstruct its color whether or not the pixel is missed in the input. We validate the novel semantic-aware implicit representation method on the image inpainting task, and the extensive experiments demonstrate that our method surpasses state-of-the-art approaches by a significant margin.

📄 PDF Abstract BibTeX arXiv:2310.09285

Code (0)

등록된 구현이 없습니다.

Tasks

Image InpaintingImage Reconstruction

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Focus 설명 없음

Similar Papers 제목 키워드 기반

Self-Supervised Face Image Restoration with a One-Shot Reference

2022-03-06 · Yanhui Guo, Fangzhou Luo, Shaoyuan Xu

For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are sus…

Image Restoration

Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection

2026-07-16 · Manuel Israel Cázares arxiv

Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal ro…

Vulnerability DetectionMathematical Reasoning

TensAIR: Real-Time Training of Neural Networks from Data-streams

2022-11-18 · Mauro D. L. Tosi, Vinu E. Venugopal, Martin Theobald

Online learning (OL) from data streams is an emerging area of research that encompasses numerous challenges from stream processing, machine learning, and networking. Stream-processing platforms, such as Apache Kafka and …

image-classificationImage ClassificationSentiment Analysis

Self-Supervised Isotropic Superresolution Fetal Brain MRI

2022-11-11 · Kay Lächler, Hélène Lajous, Michael Unser, Meritxell Bach Cuadra 외

Superresolution T2-weighted fetal-brain magnetic-resonance imaging (FBMRI) traditionally relies on the availability of several orthogonal low-resolution series of 2-dimensional thick slices (volumes). In practice, only a…

AnatomyImage Reconstruction

SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning

2026-01-29 · Jianchang Su, Yifan Zhang, Shengkai Lin, Shizhen Zhao 외 arxiv

Multi-stage ML inference pipelines are difficult to autoscale due to heterogeneous resources, cross-stage coupling, and dynamic bottleneck migration. We present SAIR, an autoscaling framework that uses an LLM as an in-co…

Reinforcement Learning