Contrastive Learning for Diverse Disentangled Foreground Generation.

European Conference on Computer Vision(2022)

引用 3|浏览74
暂无评分
摘要
We introduce a new method for diverse foreground generation with explicit control over various factors. Existing image inpainting based foreground generation methods often struggle to generate diverse results and rarely allow users to explicitly control specific factors of variation (e.g., varying the facial identity or expression for face inpainting results). We leverage contrastive learning with latent codes to generate diverse foreground results for the same masked input. Specifically, we define two sets of latent codes, where one controls a pre-defined factor (``known''), and the other controls the remaining factors (``unknown''). The sampled latent codes from the two sets jointly bi-modulate the convolution kernels to guide the generator to synthesize diverse results. Experiments demonstrate the superiority of our method over state-of-the-arts in result diversity and generation controllability.
更多
查看译文
关键词
contrastive learning,generation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要