paper-with-me

Papers

MISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis

2020-06-01 · CVPR 2020 6 · Shuchen Weng, Wenbo Li, Dawei Li, Hongxia Jin, Boxin Shi

In this paper, we explore synthesizing person images with multiple conditions for various backgrounds. To this end, we propose a framework named "MISC" for conditional image generation and image compositing. For conditional image generation, we improve the existing condition injection mechanisms by leveraging the inter-condition correlations. For the image compositing, we theoretically prove the weaknesses of the cutting-edge methods, and make it more robust by removing the spatially-invariance constraint, and enabling the bounding mechanism and the spatial adaptability. We show the effectiveness of our method on the Video Instance-level Parsing dataset, and demonstrate the robustness through controllability tests.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Image GenerationImage Generation

Similar Papers 제목 키워드 기반

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

2024-04-19 · CVPR 2024 1 · Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian 외

Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in featu…

DeblurringMotion Estimation

Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization

2026-02-15 · Guandong Li, Mengxia Ye arxiv

Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to…

Text-to-Image Generation

FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal

2026-03-19 · Telang Xu, Chaoyang Zhang, Guangtao Zhai, Xiaohong Liu arxiv

Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion…

Reflection Removal

Conditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization

2023-03-19 · Yinsong Wang, Huaqi Qiu, Chen Qin

Deep learning-based image registration approaches have shown competitive performance and run-time advantages compared to conventional image registration methods. However, existing learning-based approaches mostly require…

Hyperparameter OptimizationImage Registration

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors

2024-12-24 · Jinhyeok Choi, Heehyeon Kim, Joyce Jiyoung Whang

Graph neural networks (GNNs) have emerged as an effective tool for fraud detection, identifying fraudulent users, and uncovering malicious behaviors. However, attacks against GNN-based fraud detectors and their risks hav…

Fraud Detection