GenSpace: Benchmarking Spatially-Aware Image Generation
Humans can intuitively compose and arrange scenes in the 3D space for photography. However, can advanced AI image generators plan scenes with similar 3D spatial awareness when creating images from text or image prompts? We present GenSpace, a novel benchmark and evaluation pipeline to comprehensively assess the spatial awareness of current image generation models. Furthermore, standard evaluations using general Vision-Language Models (VLMs) frequently fail to capture the detailed spatial errors. To handle this challenge, we propose a specialized evaluation pipeline and metric, which reconstructs 3D scene geometry using multiple visual foundation models and provides a more accurate and human-aligned metric of spatial faithfulness. Our findings show that while AI models create visually appealing images and can follow general instructions, they struggle with specific 3D details like object placement, relationships, and measurements. We summarize three core limitations in the spatial perception of current state-of-the-art image generation models: 1) Object Perspective Understanding, 2) Egocentric-Allocentric Transformation and 3) Metric Measurement Adherence, highlighting possible directions for improving spatial intelligence in image generation.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingImage GenerationSimilar Papers 제목 키워드 기반
SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these models remain fundamentally limited in sp…
Text-to-Image GenerationImage EditingEigenGS Representation: From Eigenspace to Gaussian Image Space
Principal Component Analysis (PCA), a classical dimensionality reduction technique, and 2D Gaussian representation, an adaptation of 3D Gaussian Splatting for image representation, offer distinct approaches to modeling v…
Dimensionality ReductionLearning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
The eigendecomposition of the Laplace--Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains a significant bottleneck due to the high cost of iterative solvers o…
Zero-shot GeneralizationPoint CloudsAutomatic Spatially-aware Fashion Concept Discovery
This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune GoogleNet by jointly modeling clothing images and their correspo…
AttributeClusteringImage Retrieval with Multi-Modal QueryRetrievalSHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation
Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do no…