Indoor scene image generation method and device, equipment and storage medium

By performing furniture removal and feature encoding on the image to be processed, and combining it with user input information to generate the target image, the problem of fixed furniture positions in indoor scene image generation by ControlNet is solved. This achieves a balance between spatial structure stability and furniture diversity, and improves the realism and consistency of the generated effect.

CN121616702APending Publication Date: 2026-03-06BEIJING CALF INTERNET TECH CO LTD
0 Cites 2 Cited by

Patent Information

Application Number
CN202511832691.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-05
Publication Date
2026-03-06

AI Technical Summary

Technical Problem

When using ControlNet to generate indoor scene images, it is difficult to flexibly adjust the layout and types of furniture while maintaining the rationality of the spatial structure, resulting in problems such as fixed furniture positions or abnormal spatial structures.

Method used

By removing furniture from the image to be processed to generate an empty room image, and combining user input information to generate raw image prompts, feature encoding is performed using depth maps and semantic segmentation maps, and the parameters of the raw image large model are adjusted to generate the target image.

Benefits of technology

It achieves the ability to flexibly adjust the layout and types of furniture while maintaining the stability of the spatial structure, thereby improving the realism and consistency of the generated images and meeting users' personalized design needs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an indoor scene image generation method and device, equipment and a storage medium. The method comprises the following steps: firstly, acquiring a to-be-processed image with furniture and information input by a user, and performing furniture elimination processing on the image to obtain an empty room image; and then generating a cue word for image generation based on a preset cue word template in combination with user input information. Meanwhile, extracting a depth map and a semantic segmentation map of the empty room image, and inputting the depth map and the semantic segmentation map into a pre-trained depth map control model and a pre-trained semantic segmentation control model for feature coding to obtain corresponding depth control features and semantic segmentation control features. And performing parameter adjustment on the large-scale graph generation model subjected to parameter fine adjustment by using the two types of control features to obtain a target graph generation model. And finally, inputting the empty room image and the cue word into the target image generation model to obtain a target image. According to the method, the spatial structure stability and the personalized design requirement of the user on the indoor layout can be considered.
Need to check novelty before this filing date? Find Prior Art