DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition

2024-06-12 · Jiacheng Liu, Hang Zhou, Shida Wei, Rui Ma

In this paper, we address the problem of plausible object placement for the challenging task of realistic image composition. We propose DiffPop, the first framework that utilizes plausibility-guided denoising diffusion probabilistic model to learn the scale and spatial relations among multiple objects and the corresponding scene image. First, we train an unguided diffusion model to directly learn the object placement parameters in a self-supervised manner. Then, we develop a human-in-the-loop pipeline which exploits human labeling on the diffusion-generated composite images to provide the weak supervision for training a structural plausibility classifier. The classifier is further used to guide the diffusion sampling process towards generating the plausible object placement. Experimental results verify the superiority of our method for producing plausible and diverse composite images on the new Cityscapes-OP dataset and the public OPA dataset, as well as demonstrate its potential in applications such as data augmentation and multi-object placement tasks. Our dataset and code will be released.

📄 PDF Abstract BibTeX arXiv:2406.07852

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation DenoisingObject

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement

2025-10-16 · Yao Zhong, Hanzhi Chen, Simon Schaefer, Anran Zhang 외 arxiv

Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires reasoning about both semant…

Collision Avoidance

Physics-Guided Geometric Diffusion for Macro Placement Generation

2026-05-15 · Jongho Yoon, Jinsung Jeon, Seokhyeong Kang arxiv

Macro placement is a pivotal stage in VLSI physical design, fundamentally determining the overall chip performance. Recent data-driven placement methods have demonstrated significant potential, yet they often struggle to…

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

2024-12-16 · CVPR 2025 1 · Ruijie Lu, Yixin Chen, Junfeng Ni, Baoxiong Jia 외

Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yield…

Denoising Novel View Synthesis Object

Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints

2025-08-01 · Jens U. Kreber, Joerg Stueckler arxiv

Articulated objects are an important type of interactable objects in everyday environments. In this paper, we propose PhysNAP, a novel diffusion model-based approach for generating articulated objects that aligns them wi…

Point Clouds

Generating Stable Placements via Physics-guided Diffusion Models

2025-09-25 · Philippe Nadeau, Miguel Rogel, Ivan Bilić, Ivan Petrović 외 arxiv

Stably placing an object in a multi-object scene is a fundamental challenge in robotic manipulation, as placements must be penetration-free, establish precise surface contact, and result in a force equilibrium. To assess…