paper-with-me

홈 › Papers

Image Synthesis From Layout With Locality-Aware Mask Adaption

2021-01-01 · ICCV 2021 10 · Zejian Li, Jingyu Wu, Immanuel Koh, Yongchuan Tang, Lingyun Sun

This paper is concerned with synthesizing images conditioned on a layout (a set of bounding boxes with object categories). Existing works construct a layout-mask-image pipeline. Object masks are generated separately and mapped to bounding boxes to form a whole semantic segmentation mask (layout-to-mask), with which a new image is generated (mask-to-image). However, overlapped boxes in layouts result in overlapped object masks, which reduces the mask clarity and causes confusion in image generation. We hypothesize the importance of generating clean and semantically clear semantic masks. The hypothesis is supported by the finding that the performance of state-of-the-art LostGAN decreases when input masks are tainted. Motivated by this hypothesis, we propose Locality-Aware Mask Adaption (LAMA) module to adapt overlapped or nearby object masks in the generation. Experimental results show our proposed model with LAMA outperforms existing approaches regarding visual fidelity and alignment with input layouts. On COCO-stuff in 256x256, our method improves the state-of-the-art FID score from 41.65 to 31.12 and the SceneFID from 22.00 to 18.64.

📄 PDF Abstract BibTeX

Code (1)

zejianli/lama 공식 구현 pytorch

Tasks

Image GenerationObjectSemantic Segmentation

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LAMA 설명 없음

Similar Papers 제목 키워드 기반

Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis

2020-03-25 · Wei Sun, Tianfu Wu

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent em…

Image GenerationLayout-to-Image GenerationObject

Deep Consensus Learning

2021-03-15 · Wei Sun, Tianfu Wu

Both generative learning and discriminative learning have recently witnessed remarkable progress using Deep Neural Networks (DNNs). For structured input synthesis and structured output prediction problems (e.g., layout-t…

Image GenerationSegmentationSemantic Segmentation

Image Synthesis From Reconfigurable Layout and Style

2019-08-20 · ICCV 2019 10 · Wei Sun, Tianfu Wu

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from rec…

Image GenerationLayout-to-Image Generation

Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis

2024-10-09 · Ahmed Abdullah, Nikolas Ebert, Oliver Wasenmüller

Recent advancements in diffusion models have enabled a wide range of works exploiting their ability to generate high-volume, high-quality data for use in various downstream tasks. One subclass of such models, dubbed Layo…

Image GenerationLanguage ModellingLarge Language Model

Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis

2024-06-06 · CVPR 2024 1 · Marianna Ohanyan, Hayk Manukyan, Zhangyang Wang, Shant Navasardyan 외

We present Zero-Painter, a novel training-free framework for layout-conditional text-to-image synthesis that facilitates the creation of detailed and controlled imagery from textual prompts. Our method utilizes object ma…

Conditional Text-to-Image SynthesisImage Generation