Bunraku: Turning a Single Illustration into an Editable Live2D Character

• URL: http://arxiv.org/abs/2607.27348v1
• Date: Wed, 29 Jul 2026 18:06:17 GMT
• Title: Bunraku: Turning a Single Illustration into an Editable Live2D Character
• Abstract summary: We present the first system that generates all the structured information a Live2D runtime consumes.<n>Stage 1 casts layered decomposition as a layered diffusion process under a Live2D-aware organ-level taxonomy.<n>Stage 2 builds a content-conforming triangle mesh for each layer from its alpha channel alone, then predicts the keypose displacement field of all layers jointly.
• Score: 25.17979482882208
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Live2D is the dominant 2D character-animation format for anime characters and virtual avatars, representing each character as a stack of RGBA layers driven by per-layer mesh deformation. Despite its wide use in virtual streaming, mobile games, and interactive characters, authoring a Live2D model still demands weeks of manual layer separation, occlusion completion, mesh placement, and keyframing, and no prior generative method produces such a structured asset end-to-end. We present the first system that, from a single illustration, generates all the structured information a Live2D runtime consumes: ordered RGBA layers, a deformation mesh per layer, and the parameter-driven keypose vertex offsets that make the character move. Stage 1 casts layered decomposition as a layered diffusion process under a Live2D-aware organ-level taxonomy, producing an ordered RGBA stack with hidden-region completion. Stage 2 builds a content-conforming triangle mesh for each layer from its alpha channel alone, then predicts the keypose displacement field of all layers jointly: every vertex of every layer is one token, self-attention spans layer boundaries, and each displacement is factorised into a bounded direction and a log-magnitude. Joint rather than independent prediction is what makes the result a coherent character instead of separately plausible parts, and is our largest gain; scaling the network 112x yields none. On 50 held-out characters, under true generation with no teacher forcing, Stage 2 attains a per-vertex direction cosine of 0.768 (median 0.828). Because a layer's mesh derives from its alpha channel, a clothing layer can be re-textured from a natural-language instruction while the mesh and predicted animation are reused byte-for-byte. We further contribute Live2D-Bench, the first standardized benchmark for the task, and an 8,884-model Live2D corpus with layer and animation supervision.

Related papers

• R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow [50.93811008612562]
  Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets.<n>In real-world scenarios, the initial pose of a user-provided video rarely aligns with the starting frame of a reference video.<n>We propose R-DMesh, a framework designed to generate high-fidelity 4D meshes that align with video context.
  arXiv  Detail & Related papers  (2026-05-13T17:58:13Z)
• StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics [56.8957922153694]
  We present StoryBlender, a grounded 3D storyboard generation framework governed by a Story-centric Reflection Scheme.<n>StoryBlender significantly improves consistency and editability over both diffusion-based and 3D-grounded baselines.
  arXiv  Detail & Related papers  (2026-04-01T07:24:31Z)
• SPRITETOMESH: Automatic Mesh Generation for 2D Skeletal Animation Using Learned Segmentation and Contour-Aware Vertex Placement [0.0]
  SPRITETOMESH is a fully automatic pipeline for converting 2D game sprite images into triangle meshes.<n>A segmentation network trained on over 100,000 spritemask pairs from 172 games achieves an IoU of 0.87.<n>The pipeline processes a sprite in under 3 seconds, representing a speed of 300x-1200x over manual creation.
  arXiv  Detail & Related papers  (2026-02-24T17:58:31Z)
• See-through: Single-image Layer Decomposition for Anime Characters [11.629918493740263]
  We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models.<n>Our approach overcomes this by decomposing a single image into fully inpainted, semantically distinct layers with inferred drawing orders.<n>We demonstrate that our approach yields high-fidelity, manipulatable models suitable for professional, real-time animation applications.
  arXiv  Detail & Related papers  (2026-02-03T17:12:36Z)
• Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing [63.141976759536625]
  We propose Interp3D, a training-free framework for textured 3D morphing.<n>It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence.<n>For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility.
  arXiv  Detail & Related papers  (2026-01-20T16:03:22Z)
• XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation [72.12250272218792]
  We propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. We integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks. The generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.
  arXiv  Detail & Related papers  (2024-11-20T12:02:12Z)
• Efficient 3D Articulated Human Generation with Layered Surface Volumes [131.3802971483426]
  We introduce layered surface volumes (LSVs) as a new 3D object representation for articulated digital humans. LSVs represent a human body using multiple textured layers around a conventional template. They exhibit exceptional efficiency in GAN settings, where a 2D generator learns to synthesize the RGBA textures for the individual layers.
  arXiv  Detail & Related papers  (2023-07-11T17:50:02Z)
• WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction [82.79642869586587]
  WALDO is a novel approach to the prediction of future video frames from past ones. Individual images are decomposed into multiple layers combining object masks and a small set of control points. The layer structure is shared across all frames in each video to build dense inter-frame connections.
  arXiv  Detail & Related papers  (2022-11-25T18:59:46Z)
• Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields [75.81417944207806]
  This paper presents a self-supervised approach to video frame learning that requires only a single video. We parameterize the video motions by solving an ordinary differentiable equation (ODE) defined on a time-varying motion field. This implicit neural representation learns the video as a space-time continuum, allowing frame-time continuum at any temporal resolution.
  arXiv  Detail & Related papers  (2022-04-21T06:17:05Z)
• Layered Neural Atlases for Consistent Video Editing [37.69447642502351]
  We present a method that decomposes, or "unwraps", an input video into a set of layered 2D atlases. For each pixel in the video, our method estimates its corresponding 2D coordinate in each of the atlases. We design our atlases to be interpretable and semantic, which facilitates easy and intuitive editing in the atlas domain.
  arXiv  Detail & Related papers  (2021-09-23T14:58:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.