Single-image Layer Decomposition for Anime Characters
- Auto-discovered
Jian Lin, Chengze Li, Haoyun Qin, Kwun Wang Chan, Yanghua Jin, Hanyuan Liu, Stephen Chun Wang Choy, Xueting Liu
Visit resource ↗Description
Single-image Layer Decomposition for Anime Characters is the SIGGRAPH 2026 Conference Papers open-source project (See-through) that splits a static anime illustration into many inpainted semantic layers with inferred draw order.
Up to 23 layers support 2.5D-style manipulation such as parallax and editing without repainting the whole cel stack by hand.
The public repository ships inference scripts for layered PSD export, low-VRAM options, demos, and training materials for researchers and tool authors.
Anime production and ML researchers benefit most; you should know basic diffusion or inpainting pipelines and layer compositing workflows.
SIGGRAPH open-source anime layer tools draw strong interest from illustration tech communities and VTuber asset pipelines.
Link last verified accessible on 2026-09-28.
Related resources
- Drawing Thousands of Meshes with DrawMeshInstanced / Indirect (Toqoz)
Toqoz's November 2019 toqoz.fyi post walks through drawing very large mesh counts in Unity with Graphics.DrawMeshInstanced and Graphics.DrawMeshInstancedIndirect, with C# samples,
100% match · <code><advanced><drawing><last><low><project><see><single> - Reconstructing Physically Stable 3D Scenes from a Single Image
Reconstructing Physically Stable 3D Scenes from a Single Image is a single research paper with a public REST3D project site, code release, and demo videos.
100% match · <code><advanced><paper><accessible><image><last><link><project> - Dual Contouring of Signed Distance Data
Dual Contouring of Signed Distance Data is a SIGGRAPH 2026 paper with a Columbia Graphics project page linking the PDF, source, and talk materials.
100% match · <code><advanced><paper><accessible><last><link><materials><project> - MeshSplatting: Differentiable Rendering with Opaque Meshes
MeshSplatting: Differentiable Rendering with Opaque Meshes presents a mesh-based novel view synthesis method by Jan Held and collaborators that jointly optimizes geometry and…
100% match · <code><advanced><paper><lin><accessible><demos><export><last> - Neural Importance Sampling of Many Lights
Neural Importance Sampling of Many Lights presents a SIGGRAPH 2025 Conference Papers method by Pedro Figueiredo, Qihao He, Steve Bako, and Nima Khademi Kalantari for learning…
100% match · <code><advanced><paper><accessible><conference><last><link><papers> - Neural Visibility Cache for Real-Time Light Sampling
Neural Visibility Cache for Real-Time Light Sampling is a Journal of Computer Graphics Techniques Vol.
100% match · <code><advanced><paper><accessible><inference><last><link><open> - SIGGRAPH 2025 Links
SIGGRAPH 2025 Links is a curated blog roundup by Stephen Hill that indexes public materials from SIGGRAPH 2025 rather than presenting a single talk or paper. It groups…
100% match · <conference><demos><materials><open><papers><siggraph><single><source> - Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion
Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion.
99% match · <code><advanced><paper><lin><accessible><last><layer><layers> - Neural Render Proxies for Interactive and Differentiable Lighting
Neural Render Proxies for Interactive and Differentiable Lighting introduces a scene-specific neural render proxy that decouples path sampling from emission so static scenes with…
98% match · <code><advanced><paper><accessible><image><last><link><materials> - Parallelised Differentiable Straightest Geodesics for 3D Meshes
Parallelised Differentiable Straightest Geodesics for 3D Meshes presents a CIRCLE Group Imperial College London CVPR 2026 paper by Hippolyte Verninas, Caner Korkmaz, Stefanos…
98% match · <code><advanced><paper><accessible><demos><last><link><project> - GSWT: Gaussian Splatting Wang Tiles
GSWT: Gaussian Splatting Wang Tiles presents a SIGGRAPH Asia 2025 method by Yunfan Zeng, Li Ma, and Pedro V.
98% match · <code><advanced><paper><accessible><last><link><project><semantic> - Practically Utilizing Neural Networks in CPU-based Production Rendering
Practically Utilizing Neural Networks in CPU-based Production Rendering presents a Journal of Computer Graphics Techniques paper by Steve Bako, Ryusuke Villemin, and Magnus…
98% match · <code><advanced><paper><accessible><inference><last><link><low> - A Texture Streaming Pipeline for Real-Time GPU Ray Tracing
A Texture Streaming Pipeline for Real-Time GPU Ray Tracing is a SIGGRAPH 2025 Talks paper by Mark Lee, Nathan Zeichner, and Yining Karl Li from Disney Animation on streaming Ptex…
98% match · <code><advanced><paper><accessible><last><link><project><siggraph> - Real-time Image-based Lighting of Glints
Real-time Image-based Lighting of Glints.
98% match · <code><advanced><paper><accessible><image><last><link><materials> - Real-Time Neural Network Implementation for GPUs
Real-Time Neural Network Implementation for GPUs is an open-source library / codebase hosted on GitHub. Open-source companion code for the GPU Zen 4 chapter on real-time neural…
96% match · <code><advanced><image><inference><open><provides><repository><scripts> - CUDA Tile IR
CUDA Tile IR is an NVIDIA open-source GitHub repository for an MLIR-based intermediate representation and compiler stack aimed at tile-based CUDA kernel optimization on NVIDIA…
96% match · <code><advanced><layer><low><open><project><repository><source> - OpenPBR: Novel Features and Implementation Details
OpenPBR: Novel Features and Implementation Details is a technical companion paper by Jamie Portsmouth (Autodesk), Peter Kutz (Adobe), and Stephen Hill (Lucasfilm) for the OpenPBR…
92% match · <advanced><paper><accessible><last><layered><layers><link><materials> - Jackknife Transmittance and MIS Weight Estimation
Jackknife Transmittance and MIS Weight Estimation is a SIGGRAPH Asia 2025 paper by Christoph Peters, published in ACM Transactions on Graphics and summarized on the Moments in…
92% match · <advanced><paper><accessible><last><link><project><siggraph><style> - Derivatives of Spherical Harmonics
Derivatives of Spherical Harmonics presents a High-Performance Graphics 2025 poster by Christoph Peters with formulas for partial derivatives of any order of the spherical…
92% match · <advanced><paper><accessible><last><link><materials><order><project> - Steerable Perlin Noise
Steerable Perlin Noise presents a SIGGRAPH Talks 2025 note by Jacob Rice of Walt Disney Animation Studios that adds controllable anisotropy to classic Perlin noise while keeping…
90% match · <paper><accessible><last><link><materials><siggraph><style><verified>