paper-with-me

Papers

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

2020-07-02 · NeurIPS 2020 12 · Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi

We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained end-to-end on raw, unlabeled data. RELATE combines an object-centric GAN formulation with a model that explicitly accounts for correlations between individual objects. This allows the model to generate realistic scenes and videos from a physically-interpretable parameterization. Furthermore, we show that modeling the object correlation is necessary to learn to disentangle object positions and identity. We find that RELATE is also amenable to physically realistic scene editing and that it significantly outperforms prior art in object-centric scene generation in both synthetic (CLEVR, ShapeStacks) and real-world data (cars). In addition, in contrast to state-of-the-art methods in object-centric generative modeling, RELATE also extends naturally to dynamic scenes and generates videos of high visual fidelity. Source code, datasets and more results are available at http://geometry.cs.ucl.ac.uk/projects/2020/relate/.

📄 PDF Abstract BibTeX arXiv:2007.01272

Code (1)

hyenal/relate 공식 구현 pytorch

Tasks

ObjectScene Generation

Similar Papers 제목 키워드 기반

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

2023-12-08 · NeurIPS 2023 11 · Yunhao Ge, Hong-Xing Yu, Cheng Zhao, Yuliang Guo 외

A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets. While augmenting real scenes with virtual objects holds promise to improve both the diversity and quan…

3D Object DetectionData AugmentationDiversityMonocular 3D Object Detection+3

Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach

2023-07-27 · Sandika Biswas, Kejie Li, Biplab Banerjee, Subhasis Chaudhuri 외

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single m…

3D ReconstructionRobot Navigation

InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects

2025-09-28 · Xinhao Cai, Minghang Zheng, Xin Jin, Yang Liu arxiv

We propose a novel task of text-controlled human object interaction generation in 3D scenes with movable objects. Existing human-scene interaction datasets suffer from insufficient interaction categories and typically on…

Collision AvoidanceVisual Grounding

CP4D: Compositional Physics-aware 4D Scene Generation

2026-06-08 · Hanxin Zhu, Cong Wang, Tianyu He, Long Chen 외 arxiv

4D generation (\textit{i.e.}, dynamic 3D generation) has recently emerged as a rapidly growing research frontier due to its powerful spatiotemporal modeling capabilities. However, despite notable advances, existing appro…

Scene GenerationMotion Synthesis3D Generation

REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image

2026-05-28 · Xiaoxuan Ma, Jiashun Wang, Nicolas Ugrinovic, Yehonathan Litman 외 arxiv

Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, …

Image ReconstructionScene UnderstandingScene Generation