Abstract We present Layer3D, a novel 3D neural representation that models objects as collections of decomposable neural implicit primitives. These primitives enable the generation of layered images with consistent correspondences across viewpoints, establishing a flexible framework for multiview vector graphics decomposition. Integrated into a text‐to‐3D pipeline via Score Distillation Sampling (SDS), Layer3D learns to generate primitives with diverse shape topologies while preserving structural coherence. To ensure front‐to‐back ordering required for 2D flat graphics, our method incorporates front‐to‐back rendering and shape regularization constraints. Experimental results demonstrate that Layer3D consistently produces meaningful, topology‐diverse layers across multiple views, thereby facilitating intuitive and effective layer‐based vector editing.

The Hong Kong University of Science and Technology (Guangzhou), China and The Hong Kong University of Science and Technology, China Establishing one-to-one stroke correspondences is fundamental to vector-based animation inbetweening. Animators may face great challenges when handling occlusion, as occluded strokes must be drawn explicitly in keyframes and manually hidden frame by frame after stroke interpolation. To reduce tedious effort, we present LayerInbetween , an occlusion-aware framework for vector stroke correspondence and automatic inbetweening. It performs automatic layering to guide stroke tracing and correspondence finding for occluded strokes, and to resolve occlusion with layers in the inbetween frames. To predict occluded strokes, we propose a Global-Local Layer Transformation (GLLT) module that progressively improves the spatial alignment of strokes across keyframes via layer guidance, thereby indicating their potential positions. Our framework is trained on a synthetic dataset comprising 17k+ pairs of keyframes with occlusion and their stroke correspondences. Extensive experiments demonstrate the effectiveness of LayerInbetween compared with existing methods and its generalization capabilities to various types of drawings. In addition to its superior performance, our vector-based inbetweening method enables more flexible editing of 2D animation than raster-based video generation. Code and data for this paper are available at https://github.com/MarkMoHR/LayerInbetween.