SIGGRAPH 2025 papers on the web

This page tracks the new paper links made to our list of SIGGRAPH 2025 papers.

Page maintained by Ke-Sen Huang. If you have additions or changes, send an e-mail.

September 5, 2025

• DesignManager: An Agent-Powered Copilot for Designers to Integrate AI Design Tools into Creative Workflows (SIG/TOG)
• Kinematic Motion Retargeting for Contact-Rich Anthropomorphic Manipulations (SIG/TOG)
• Revisiting Tradition and Beyond: A Customized Bilateral Filtering Framework for Point Cloud Denoising (SIG/TOG)
• A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds with 0-1 Integer Optimization (SIG/TOG)
• Light Pipe Holographic Display: Bandwidth-preserved Kaleidoscopic Guiding for AR Glasses (SIG/TOG)
• HoloChrome: Polychromatic Illumination for Speckle Reduction in Holographic Near-Eye Displays (TOG)
• Noise-Coded Illumination for Forensic and Photometric Video Analysis (TOG)
• Collaborative On-Sensor Array Cameras (SIG/TOG)
• A Monte Carlo Rendering Framework for Simulating Optical Heterodyne Detection (SIG/TOG)
• LAM: Large Avatar Model for One-shot Animatable Gaussian Head (SIG)
• SOAP: Style-Omniscient Animatable Portraits (SIG)
• 3DGH: 3D Head Generation with Composable Hair and Face (SIG/TOG)
• Facial Microscopic Structures Synthesis from a Single Unconstrained Image (SIG)
• Towards Comprehensive Neural Materials: Dynamic Structure-Preserving Synthesis with Accurate Silhouette at Instant Inference Speed (SIG)
• NAM: Neural Adjoint Maps for refining shape correspondences (SIG/TOG)
• GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations (SIG/TOG)
• Unsupervised Decomposition of 3D Shapes into Expressive and Editable Extruded Profile Primitives (SIG)
• OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation (SIG)
• BANG: Dividing 3D Assets via Generative Exploded Dynamics (SIG/TOG)
• Spherical Lighting with Spherical Harmonics Hessian (SIG)

September 3, 2025

• StructRe: Rewriting for Structured Shape Modeling (TOG)
• Designing 3D Anisotropic Frame Fields with Odeco Tensors (SIG/TOG)
• Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation (SIG/TOG)
• PDT: Point Distribution Transformation with Diffusion Models (SIG)
• CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation (SIG)
• DeFillet: Detection and Removal of Fillet Regions in Polygonal CAD Models (SIG/TOG)
• GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians (SIG)
• Feature-Preserving Mesh Repair via Restricted Power Diagram (SIG)

August 28, 2025

• Order Matters: Learning Element Ordering for Graphic Design Generation (SIG/TOG)
• Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture (SIG/TOG)
• A Platform for Interactive AI Character Experiences (SIG)
• Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion (SIG)
• Spline Deformation Field (SIG)
• High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion (SIG)
• Controllable Tracking-Based Video Frame Interpolation (SIG)
• Learning to Draw Is Learning to See: Analyzing Eye Tracking Patterns for Assisted Observational Drawing (SIG)
• HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination (SIG)
• ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation (SIG)
• VirCHEW Reality: On-Face Kinesthetic Feedback for Enhancing Food-Intake Experience in Virtual Reality (SIG)
• Splat and Replace: 3D Reconstruction with Repetitive Elements (SIG)
• SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting (SIG/TOG)
• Echoes of the Coliseum: Towards 3D Live streaming of Sports Events (SIG/TOG)
• NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity (TOG)
• A Closest Point Method for PDEs on Manifolds with Interior Boundary Conditions for Geometry Processing (TOG)
• Faraday Cage Estimation of Normals for Point Clouds and Ribbon Sketches (SIG/TOG)
• A Polyhedral Construction of Empty Spheres in Discrete Distance Fields (SIG)
• Progressive Dynamics++: A Framework for Stable, Continuous, and Consistent Animation Across Resolution and Time (SIG/TOG)
• Lifting the Winding Number: Precise Discontinuities in Neural Fields for Physics Simulation (SIG)
• Shape Space Spectra (SIG/TOG)

August 24, 2025

• TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space
• FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios
• Fast Subspace Fluid Simulation with a Temporally-Aware Basis
• Gaussian Fluids: A Grid-Free Fluid Solver based on Gaussian Spatial Representation
• Quadtree Tall Cells for Eulerian Liquid Simulation

August 21, 2025

• Hybrid Tours: A Clip-based System for Authoring Long-take Touring Shots
• Multi-Dimensional Procedural Wave Noise
• Neurally Integrated Finite Elements for Differentiable Elasticity on Evolving Domains
• Lightning-fast Boundary Element Method
• Conformal First Passage for Epsilon-free Walk-on-Spheres
• Guiding-Based Importance Sampling for Walk on Stars
• Image-space Adaptive Sampling for Fast Inverse Rendering
• Unbiased Differential Visibility Using Fixed-Step Walk-on-Spherical-Caps And Closest Silhouettes
• Appearance-Preserving Scene Aggregation for Level-of-Detail Rendering
• Reservoir Splatting for Temporal Path Resampling and Motion Blur
• GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

August 14, 2025

• Model See Model Do: Speech-Driven Facial Animation with Style Control
• Generative detail enhancement for physically based materials
• Physically Controllable Relighting of Photographs
• Neural Co-Optimization of Structural Topology, Manufacturable Layers, and Path Orientations for Fiber-Reinforced Composites
• StreamME: Simplify 3D Gaussian Avatar within Live Stream
• EditDuet: A Multi-Agent System for Video Non-Linear Editing
• Style Customization of Text-to-Vector Generation with Image Diffusion Priors
• Motion Inversion for Video Customization
• RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
• Automated Task Scheduling for Cloth and Deformable Body Simulations in Heterogeneous Computing Environments
• Physics-inspired Estimation of Optimal Cloth Mesh Resolution
• Fast Physics-Based Modeling of Knots and Ties using Templates
• Intersection-Free Garment Retargeting
• Geometric Contact Potential
• Painless Differentiable Rotation Dynamics
• MiSo: A DSL for Robust and Efficient Solve and Minimize Problems
• Topological Offsets
• Feature-Aligned Parametrization in Penner Coordinates

July 17, 2025

• Large-Scale Multi-Character Interaction Synthesis

July 10, 2025

• Quadric-Based Silhouette Sampling for Differentiable Rendering
• Moment Bounds are Differentiable: Efficiently Approximating Measures in Inverse Rendering
• Instant Self-Intersection Repair for 3D Meshes
• DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
• The Mokume Dataset and Inverse Modeling of Solid Wood Textures
• GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies
• Rags2Riches: Computational Garment Reuse
• Motion Control via Metric-Aligning Motion Matching
• Computational Modeling of Gothic Microarchitecture
• Closed-form Generalized Winding Numbers of Rational Parametric Curves for Robust Containment Queries
• Polynomial 2D Biharmonic Coordinates for High-order Cages
• Field Smoothness-Controlled Partition for Quadrangulation
• MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation

July 3, 2025

• Controllable Complex Freezing Dynamics Simulation on Thin Films
• Fast Isotropic Median Filtering
• Texture Size Reduction Through Symmetric Overlap and Texture Carving
• Single Edge Collapse Quad-Dominant Mesh Reduction
• Neural Importance Sampling of Many Lights
• MoVer: Motion Verification for Motion Graphics Animations
• Instance Segmentation of Scene Sketches Using Natural Image Priors
• MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation
• Hand-Shadow Poser
• MonetGPT: Solving Puzzles Enhances MLLMs’ Image Retouching Skills
• PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models
• MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
• PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction

June 26, 2025

• AnyTop: Character Animation Diffusion with Any Topology
• SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation
• Be Decisive: Noise-Induced Layouts for Multi-Subject Generation
• HoLa: B-Rep Generation using a Holistic Latent Representation
• pOps: Photo-Inspired Diffusion Operators
• IP-Composer: Semantic Composition of Visual Concepts
• Nested Attention: Semantic-aware Attention Values for Concept Personalization
• Dynamic Concepts Personalization from Single Videos
• CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
• Aerial Path Online Planning for Urban Scene Updation
• Modeling and Rendering Glow Discharge
• Vector-Valued Monte Carlo Integration Using Ratio Control Variates
• Transforming Unstructured Hair Strands into Procedural Hair Grooms
• Generative Neural Materials
• Neural BRDF Importance Sampling by Reparameterization
• Position-Normal Manifold for Efficient Glint Rendering on High-Resolution Normal Maps
• RNA: Relightable Neural Assets
• MaterialPicker: Multi-Modal DiT-Based Material Generation
• IntrinsicEdit: Precise generative image manipulation in intrinsic space
• 3D-Fixup: Advancing Photo Editing with 3D Priors
• Elastic Locomotion with Mixed Second-order Differentiation
• Leapfrog Flow Maps for Real-Time Fluid Simulation
• Fluid Simulation on Compressible Flow Maps
• EDGE: Epsilon-Difference Gradient Evolution for Buffer-Free Flow Maps
• Clebsch Gauge Fluid on Particle Flow Maps
• Cirrus: Adaptive Hybrid Particle-Grid Flow Maps on GPU
• Fluid Simulation on Vortex Particle Flow Maps
• A Neural Particle Level Set Method for Dynamic Interface Tracking
• JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics
• Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics
• 3DGS2: Near Second-order Converging 3D Gaussian Splatting
• High-performance CPU Cloth Simulation Using Domain-decomposed Projective Dynamics
• Offset Geometric Contact
• Stable Cosserat Rods
• Augmented Vertex Block Descent
• Real-Time Knit Deformation and Rendering
• Curl Quantization for Automatic Placement of Knit Singularities

June 21, 2025

• Sync with Official Program

June 19, 2025

• Hyper-Dimensional Deformation Simulation
• Optimal r-Adaptive In-Timestep Remeshing for Elastodynamics
• AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization

June 12, 2025

• Adaptive Phase-Field-FLIP for Very Large Scale Two-Phase Fluid Simulation
• Stressful Tree Modeling: Breaking Branches with Strands
• Arenite: A Physics-based Sandstone Simulator
• DeepMill: Neural Accessibility Learning for Subtractive Manufacturing
• NeurCross: A Neural Approach to Computing Cross Fields for Quad Mesh Generation
• Facial Appearance Capture at Home with Patch-Level Reflectance Prior

June 5, 2025

• EVA: Expressive Virtual Avatars from Multi-view Videos
• TeGA: Texture Space Gaussian Avatars for High-Resolution DynamicHead Modeling
• Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
• Gaussian Wave Splatting for Computer Generated Holography
• Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting
• On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
• Adaptive Algebraic Reuse of Reordering in Cholesky Factorizations with Dynamic Sparsity Patterns
• Optimal r-Adaptive In-Timestep Remeshing for Elastodynamics
• ANIME-Rod: Adjustable Nonlinear Isotropic Materials for Elastic Rods
• Progressive Dynamics++: A Framework for Stable, Continuous, and Consistent Animation Across Resolution and Time
• When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering
• ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
• VR-Doh: Hands-on 3D Modeling in Virtual Reality
• CK-MPM: A Compact-Kernel Material Point Method
• StiffGIPC: Advancing GPU IPC for stiff affine-deformable simulation
• Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

June 3, 2025

• Dynamic Mesh Processing on the GPU
• Differentiable Geometric Acoustic Path Tracing using Time-Resolved Path Replay Backpropagation
• Bernstein Bounds for Caustics
• Multiple Importance Reweighting for Path Guiding
• Monocular Online Reconstruction with Enhanced Detail Preservation
• Towards Comprehensive Neural Materials: Dynamic Structure-Preserving Synthesis with Accurate Silhouette at Instant Inference Speed
• HexHex: Highspeed Extraction of Hexahedral Meshes
• PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers
• Sphere Carving: Bounding Volumes for Signed Distance Fields
• RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

May 25, 2025

• C-Tubes: Design and Optimization of Tubular Structures Composed of Developable Strips
• Differentiable Geometric Acoustic Path Tracing using Time-Resolved Path Replay Backpropagation
• TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians
• LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
• Semantically Consistent Text-to-Motion with Unsupervised Styles
• AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
• Text-based Animatable 3D Avatars with Morphable Model Alignment
• AlignTex: Pixel-Precise Texture Generation from Multi-view Artwork

May 22, 2025

• TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization
• Uncertainty for SVBRDF Acquisition using Frequency Analysis
• Inverse Geometric Locomotion
• Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Medias
• PhysicsFC: Learning User-Controlled Skills for a Physics-Based Football Player Controller
• Towards Understanding Depth Perception in Foveated Rendering
• Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
• Deformable Beta Splatting
• Solving partial differential equations in participating media
• Rectangular Surface Parameterization
• Putting Rigid Bodies to Rest

May 15, 2025

• Linear-Time Transport with Rectified Flows
• Sobol' Sequences with Guaranteed-Quality 2D Projections
• Page Created and Published