DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation

TL;DR

DisPositioNet introduces a self-supervised model that disentangles pose and identity features in scene graphs, enabling more realistic and diverse image manipulations by modifying object attributes without losing visual fidelity.

Contribution

The paper presents a novel self-supervised framework for disentangling pose and identity in scene graph-based image manipulation, improving realism and diversity of generated images.

Findings

Outperforms previous methods qualitatively and quantitatively

Enables diverse image generation through probabilistic sampling

Maintains object identity and pose during manipulation

Abstract

Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph. Although existing works have shown promising results in modifying the placement and pose of objects, scene manipulation often leads to losing some visual characteristics like the appearance or identity of objects. In this work, we propose DisPositioNet, a model that learns a disentangled representation for each object for the task of image manipulation using scene graphs in a self-supervised manner. Our framework enables the disentanglement of the variational latent embeddings as well as the feature representation in the graph. In addition to producing more realistic images due to the decomposition of features like pose and identity, our method takes advantage of the probabilistic sampling in the intermediate features to generate more diverse images in object replacement or addition tasks. The results of our experiments show that disentangling the feature representations in the latent manifold of the model outperforms the previous works qualitatively and quantitatively on two public benchmarks. Project Page: https://scenegenie.github.io/DispositioNet/