Related papers: Toward Scene Graph and Layout Guided Complex 3D Sc…
Recent advances in large language models (LLMs) have significantly improved language-driven 3D content generation, but most existing approaches still treat scene generation and user interaction as separate processes, limiting the…
Recent progress in the text-driven 3D stylization of a single object has been considerably promoted by CLIP-based methods. However, the stylization of multi-object 3D scenes is still impeded in that the image-text pairs used for…
3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid…
While Open Set Semantic Mapping and 3D Semantic Scene Graphs (3DSSGs) are established paradigms in robotic perception, deploying them effectively to support high-level reasoning in large-scale, real-world environments remains a significant…
This paper proposes a novel framework for generating lingual descriptions of indoor scenes. Whereas substantial efforts have been made to tackle this problem, previous approaches focusing primarily on generating a single sentence for each…
Recent advancements in 3D generation have leveraged synthetic datasets with ground truth 3D assets and predefined cameras. However, the potential of adopting real-world datasets, which can produce significantly more realistic 3D scenes,…
Semantics has enabled 3D scene understanding and affordance-driven object interaction. However, robots operating in real-world environments face a critical limitation: they cannot anticipate how objects move. Long-horizon mobile…
3D generation from natural language offers significant potential to reduce expert manual modeling efforts and enhance accessibility to 3D assets. However, existing methods often yield unstructured meshes and exhibit poor interactivity,…
Current 3D scene graph generation (3DSGG) approaches heavily rely on a single-agent assumption and small-scale environments, exhibiting limited scalability to real-world scenarios. In this work, we introduce Multi-Agent 3D Scene Graph…
Well-designed indoor scenes should prioritize how people can act within a space rather than merely what objects to place. However, existing 3D scene generation methods emphasize visual and semantic plausibility, while insufficiently…
Generating images from scene graphs is a challenging task that attracted substantial interest recently. Prior works have approached this task by generating an intermediate layout description of the target image. However, the representation…
Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing…
This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to…
3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type,…
Designing 3D scenes is traditionally a challenging task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes…
Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…
We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…
3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent representation, but also to the fact that most scene-level 3D visual data exists in the form…
LiDAR scene synthesis is an emerging solution to scarcity in 3D data for robotic tasks such as autonomous driving. Recent approaches employ diffusion or flow matching models to generate realistic scenes, but 3D data remains limited compared…
Recent years have seen an explosion of work and interest in text-to-3D shape generation. Much of the progress is driven by advances in 3D representations, large-scale pretraining and representation learning for text and image data enabling…