Interactive Image Manipulation with Natural Language Instruction Commands
This work addresses the need for more controllable natural language-conditioned image generation, though it appears incremental as it builds on existing latent space methods.
The authors tackled the problem of interactive image manipulation using natural language instructions, enabling users to modify a source image into a target image based on textual descriptions, with experimental results showing successful generation on their dataset.
We propose an interactive image-manipulation system with natural language instruction, which can generate a target image from a source image and an instruction that describes the difference between the source and the target image. The system makes it possible to modify a generated image interactively and make natural language conditioned image generation more controllable. We construct a neural network that handles image vectors in latent space to transform the source vector to the target vector by using the vector of instruction. The experimental results indicate that the proposed framework successfully generates the target image by using a source image and an instruction on manipulation in our dataset.