Generating Visual Spatial Description via Holistic 3D Scene Understanding
Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem of skewed spatial understanding of target objects. In this work, we investigate the incorporation of 3D scene features for VSD. With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes. Besides, we propose a scene subgraph selecting mechanism, sampling topologically-diverse subgraphs from Go3D-S2G, where the diverse local structure features are navigated to yield spatially-diversified text generation. Experimental results on two VSD datasets demonstrate that our framework outperforms the baselines significantly, especially improving on the cases with complex visual spatial relations. Meanwhile, our method can produce more spatially-diversified generation. Code is available at https://github.com/zhaoyucs/VSD.
Code (1)
Tasks
Scene UnderstandingText GenerationSimilar Papers 제목 키워드 기반
Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval
Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2…
Image RetrievalObjectobject-detectionObject Detection+1A Sentence Is Worth a Thousand Pixels
We are interested in holistic scene understanding where images are accompanied with text in the form of complex sentential descriptions. We propose a holistic conditional random field model for semantic parsing which rea…
Re-RankingScene UnderstandingSegmentationSemantic Parsing+2ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolv…
3D visual groundingVisual GroundingGenerating Human Motion in 3D Scenes from Text Descriptions
Generating human motions from textual descriptions has gained growing research interest due to its wide range of applications. However, only a few works consider human-scene interactions together with text conditions, wh…
Motion GenerationObjectSpatial ReasoningSpatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models
New era has unlocked exciting possibilities for extending Large Language Models (LLMs) to tackle 3D vision-language tasks. However, most existing 3D multimodal LLMs (MLLMs) rely on compressing holistic 3D scene informati…