HECTOR: Hybrid Editable Compositional Object References for Video Generation
Real-world videos naturally portray complex interactions among distinct physical objects, effectively forming dynamic compositions of visual elements. However, most current video generation models synthesize scenes holistically and therefore lack mechanisms for explicit compositional manipulation. To address this limitation, we propose HECTOR, a generative pipeline that enables fine-grained compositional control. In contrast to prior methods,HECTOR supports hybrid reference conditioning, allowing generation to be simultaneously guided by static images and/or dynamic videos. Moreover, users can explicitly specify the trajectory of each referenced element, precisely controlling its location, scale, and speed (see Figure1). This design allows the model to synthesize coherent videos that satisfy complex spatiotemporal constraints while preserving high-fidelity adherence to references. Extensive experiments demonstrate that HECTOR achieves superior visual quality, stronger reference preservation, and improved motion controllability compared with existing approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationSimilar Papers 제목 키워드 기반
Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning
Despite neural implicit representations demonstrating impressive high-quality view synthesis capacity, decomposing such representations into objects for instance-level editing is still challenging. Recent works learn…
2D Panoptic SegmentationMetric LearningNovel View SynthesisPanoptic SegmentationPrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes
Large-scale 3D semantic scene generation has predominantly relied on voxel-based representations, which are memory-intensive, bound by fixed resolutions, and challenging to edit. In contrast, primitives represent semanti…
Scene GenerationGaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly…
3D ReconstructionCreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers
Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream…
Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures
Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs. While RGNNs have been increasingly adopted in many…
8kC++ codeGPUScheduling