Related papers: OMG: Occlusion-friendly Personalized Multi-concept…

Retrieving tracked-vehicles by natural language descriptions plays a critical role in smart city construction. It aims to find the best match for the given texts from a set of tracked vehicles in surveillance videos. Existing works…

We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…

We present PersonaCraft, a framework for controllable and occlusion-robust full-body personalized image synthesis of multiple individuals in complex scenes. Current methods struggle with occlusion-heavy scenarios and complete body…

The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single…

Real-time occlusion handling is a major problem in outdoor mixed reality system because it requires great computational cost mainly due to the complexity of the scene. Using only segmentation, it is difficult to accurately render a virtual…

Existing solutions for 3D semantic occupancy prediction typically treat the task as a one-shot 3D voxel-wise segmentation perception problem. These discriminative methods focus on learning the mapping between the inputs and occupancy map in…

Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive…

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera. Recently, deep learning-based…

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Integrating multiple personalized concepts into a single image has recently gained attention in text-to-image (T2I) generation. However, existing methods often suffer from performance degradation in complex scenes due to distortions in…

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can…

Compositing human figures into scene images has broad applications in areas such as entertainment and advertising. However, existing methods often cannot handle occlusion of the inserted person by foreground objects and unnaturally place…

Occluded person re-identification (re-ID) presents a challenging task due to occlusion perturbations. Although great efforts have been made to prevent the model from being disturbed by occlusion noise, most current solutions only capture…

Nowadays, the enhanced capabilities of in-expensive imaging devices have led to a tremendous increase in the acquisition and sharing of multimedia content over the Internet. Despite advances in imaging sensor technology, annoying conditions…

Text-to-image diffusion models exhibit remarkable generative capabilities, but lack precise control over object counts and spatial arrangements. This work introduces a two-stage system to address these compositional limitations. The first…

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on…

Diffusion customization methods have achieved impressive results with only a minimal number of user-provided images. However, existing approaches customize concepts collectively, whereas real-world applications often require sequential…

Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. When bounding boxes overlap, most existing methods lack explicit occlusion information,…