Related papers: OmniPart: Part-Aware 3D Generation with Semantic D…
Shape primitive abstraction, which decomposes complex 3D shapes into simple geometric elements, plays a crucial role in human visual cognition and has broad applications in computer vision and graphics. While recent advances in 3D content…
Recent advancements in controllable human image generation have led to zero-shot generation using structural signals (e.g., pose, depth) or facial appearance. Yet, generating human images conditioned on multiple parts of human appearance…
While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an…
Simplifying complex 3D meshes is a crucial step in robotics applications to enable efficient motion planning and physics simulation. Common methods, such as approximate convex decomposition, represent a mesh as a collection of simple parts,…
Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of…
Shape generation is the practice of producing 3D shapes as various representations for 3D content creation. Previous studies on 3D shape generation have focused on shape quality and structure, without or less considering the importance of…
Articulated 3D object generation is fundamental for creating realistic, functional, and interactable virtual assets which are not simply static. We introduce MeshArt, a hierarchical transformer-based approach to generate articulated 3D…
Recent unified 3D generation models have made remarkable progress in producing high-quality 3D assets from a single image. Notably, layout-aware approaches such as SAM3D can reconstruct multiple objects while preserving their spatial…
This paper propels creative control in generative visual AI by allowing users to "select". Departing from traditional text or sketch-based methods, we for the first time allow users to choose visual concepts by parts for their creative…
Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily…
Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this…
Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer…
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from…
Understanding and generating the fine-grained structure of objects -- such as birds with species-specific beaks, wings, and tails -- is a long-standing challenge in computer vision. We propose Chirpy3D, a part-aware multi-view diffusion…
Current text-to-3D methods excel at generating single objects but falter on compositional prompts. We argue this failure is fundamental to their optimization schedules, as simultaneous or iterative heuristics predictably collapse under a…
This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editing and generation are performed in an unsupervised manner.…
3D object generation has undergone significant advancements, yielding high-quality results. However, fall short of achieving precise user control, often yielding results that do not align with user expectations, thus limiting their…
Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent…
Recently, the emergence of diffusion models has opened up new opportunities for single-view reconstruction. However, all the existing methods represent the target object as a closed mesh devoid of any structural information, thus neglecting…
Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications. To tackle this problem, some works design task-specific solutions by translating human understanding of the task…