3D Object Manipulation in a Single Image Using Generative Models
Keywords: 3d object manipulation, diffusion models, image editing, image animation
Abstract: Object manipulation in images aims to not only edit the object presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling static editing and dynamic motion applications, while also struggling to achieve realism in object appearance and scene lighting. In this work, we introduce OMG3D, a novel framework that integrates the precise geometric control with the generative power of diffusion models, thus achieving significant enhancements in visual performance. Our framework converts 2D objects into 3D, enabling user-directed modifications and lifelike motions at the geometric level. To address texture realism, we propose CustomRefiner, a texture refinement module that pretrain a customized diffusion model to align the style and perspectives of coarse renderings with the original image. Additionally, we introduce IllumiCombiner, an lighting processing module that estimates and adjusts background lighting to match human visual perception, resulting in more realistic illumination. Extensive experiments demonstrate the outstanding visual performance of our approach in both static and dynamic scenarios. Remarkably, all these steps can be done using one NVIDIA 3090. The code and project page will be released upon acceptance of the paper.
Supplementary Material: zip
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2162
Loading