SIGGRAPH 2026 Technical Papers
Technical Papers grouped by their official SIGGRAPH 2026 program sessions. Paper titles link to their ACM Digital Library records. Awards follow the official SIGGRAPH announcement.
Best Paper Honorable Mention
Monday, 20 July
Digital Humans & Virtual Try-On
- FabricTryOn: Taming Image Editing Models for Garment Re-Texturing
- DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
- MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
- Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
- HumanFlow: Controllable Human Image Generation via Flow Matching
Numerical Geometry a la Mode
- Boundary-aware Neural Model Reduction for PDEs
- Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
- Efficient Multiscale Lanczos Eigenpair Extraction
- Component Modes Synthesis Method with Multiple Partitions for Large-scale Eigenvalue Problem
Generative 3D & Editing
- Iris3D: 3D Generation via Synchronized Diffusion Distillation
- CubePart: An Open-Vocabulary Part-Controllable 3D Generator
- Pixal3D: Pixel-Aligned 3D Generation from Images
- InvSculpt: Inverse Sculpting Modeling via Controlled 3D Generation and a Vector Displacement Field
- VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
- Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
- ShapeUP: Scalable Image-Conditioned 3D Editing
Holography & Displays
- Invisible Holographic Window: Full-color 3D Image Reconstruction from Transparent Surface-relief Computer-generated Holograms
- PAColorHolo: A Perceptually-Aware Color Management Framework for Holographic Displays
- Single-View Holographic Volumetric 3D Printing with Coupled Differentiable Wave-Optical and Photochemical Optimization
- HoloPathTracer: Fast and Accurate Wave Path Tracing for Holography
- Complex-Valued Holographic Radiance Fields
- MorphSkein: A Shape-Changing Afterimage Display Preserving Pixel Density During Surface-Area Changes Across Troposkein-Based Shapes
- CoherentRaster: Efficient 3D Gaussian Splatting for Light Field Displays
Learning for CAD
- DualBrep: A Dual-Field Continuous Representation for B-rep Modelling
- Autoregressive B-Rep Shape Generation with Parametric Surfaces
- B-repLer: Language-guided Editing of CAD Models
- Flatten the Complex: Joint B-Rep Generation via Compositional k-Cell Particles
- BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
- Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion
Winding Numbers & Surface Representations
- Fast and Exact Winding Numbers for Triangle Meshes
- Spatially Accelerated Winding Numbers for Curved Geometry
- Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers
- The Antipodal Method: Fast, Accurate, and Robust 3D Generalized Winding Numbers
- ADS: Random Sampling of Occupancy Functions using Adaptive Delaunay Scaffolding
- Differentiable Voxelization of Surface Representations
- Uncertainty-aware geometry processing on Gaussian Process Implicit SurfacesHonorable Mention
3D Gaussian Splatting I
- Hybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering
- Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification
- Gaussian Point Splatting
- SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian Splatting
- A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
- Mobile3DGS³: Accelerate Mobile 3DGS Rendering via Gradient-Aware Super-Sampling and Frame Interpolation
Faces & Avatars
- Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
- Emotion Manipulation for Talking-Head Videos via Facial Landmarks
- Learning a Delighting Prior for Facial Appearance Capture in the Wild
- Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation
- EchoAvatar: Real-time Generative Avatar Animation from Audio Streams
- See-through: Single-image Layer Decomposition for Anime Characters
Speedy 3D
- gCDT: A Highly Parallel GPU Algorithm for Large-Scale Constrained Delaunay Triangulation
- Scalable GPU Construction of 3D Voronoi and Power Diagrams
- GPU-accelerated Certified Hausdorff Distance Between Triangle Meshes
- PQ-Free HD: Priority-Queue-Free Hausdorff Distance for Triangle Meshes on GPU
- Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds
- Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations
Video Generation
- MV-S2V: Multi-View Subject-Consistent Video Generation
- OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
- ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
- HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
- UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Creating & Iso-Surfacing SDFs
- Points as Tori: Fast Pointwise Signed Distance for Point Clouds
- SuperSDF:Sparse SDF Super-Resolution for Surface Extraction
- SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
- The PhaseTree: Multiphase Signed Distance Fields
- Dual Contouring of Signed Distance Data
- Dual Contouring over Expanded Cubes (DCx) for Zero-Level Set Extraction from Neural Unsigned Distance Functions
- Subgrid Marching Tetrahedra
Fabrication
- AtomSlicer: Constant-Thickness Field-Aligned Non-Planar Slicing and Continuous Toolpaths for FFF
- FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells
- Mechanical Cloaking of Halftoned Imagery
- Shellular Metamaterial Design via Compact Electric Potential Parametrization
- DeepMill++: Neural Guidance Meets Rasterization for Efficient Accessibility Analysis
- Uniformly Deployable Kirigami on Arbitrary Planar Graphs
- IsoGami: Rigid-Deployable Kirigami Materials From Isohedral Tilings
Humans & Hands - Reconstruction
- TwinPose: Person-Specific Subspaces for Multi-View 3D Pose Estimation
- AMOR: Airborne Motion Reconstruction via Homotopy-Aware Trajectory Optimization
- FLASHand: Feed-forward reLightable and Animatable Single-view Hand Reconstruction
- AGILE: Hand-object Interaction Reconstruction from Video via Agentic Generation
- EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera
- OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer
Real-Time Rendering
- Streaming of rendered content with adaptive frame rate and resolution
- Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering
- LightOpt: Lights Optimization for Real-time Rendering
- DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation
- Generalized Spherical Harmonics Products using Spherical Grids
Tuesday, 21 July
Fluid Reconstruction & Optimization
- GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction
- LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
- Fast VEM Fluid Simulation
- DiffSurFlow: Efficient and Robust Differentiable Fluid Optimization via Surrogate Strategy on Flow Map
- Generic Variational Spacetime Optimization of Vortex Core Manifolds
Generative 3D (2)
- SegviGen: Repurposing 3D Generative Model for Part Segmentation
- SimArt: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM
- Neural Cellular Automata: From Cells to Pixels
- Neural Particle Automata: Learning Self-Organizing Particle Dynamics
- PixTex: Consistent 3D Texturing via Pixel-Space Multi-View Diffusion
- Generative 3D Gaussians with Learned Density Control
Layouts & Procedural
- LLM-enhanced Scene Graph Learning for Household Rearrangement
- CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
- Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction
- Toward Richer Material Generation via Procedural Data Enhancement
- InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation
- RCGP: Resource Contracts for Graphics Programming
Video Gen & Camera Control
- Video Analysis and Generation via a Semantic Progress Function
- Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
- ReRoPE: Repurposing RoPE for Relative Camera Control
- FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
- UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
- CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation
3D Generation
- Nexus: Native Mesh Generation with Diffusion
- Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes
- Tempo3D: Efficient Temporal-Aware Fine-Tuning and Multi-View Latent Aggregation for 3D Generation
- PEGAsus: 3D Personalization of Geometry and Appearance
- AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation
- MeshFlow: Mesh Generation with Equivariant Flow Matching
- Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Dynamic Scenes
- MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors
- SmoothMotionVectors: Optimizing Your Content for Video Codecs in Free View Video Compression
- CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
- TSMC: Time-varying 4D Scene Mesh Compression
- Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
- Articulate That Object Part (ATOP): 3D Part Articulation from Text and via Motion Personalization
Materials & Textures
- Controllable Texture Tiling via Diffusion Transformers with Transformed Rotary Embeddings
- VideoNeuMat: Neural Material Extraction from Generative Video Models
- PureSample: Neural Materials Learned by Sampling Microgeometry
- Fast and Accurate Gaussian Process Modelling of Real-World Materials
- Successive Height Preintegration for a Height-Interdependent Path Formulation of Multiple Bounces in Smith Microfacet BRDFs
- Robust In-Engine Texture Optimization from Inconsistent Generative Targets
Phased & Viscous Fluids
- Spatiotemporal FLIP for Fast Free-Surface and Two-Phase Simulation With Very Large Time StepsHonorable Mention
- Buoyancy-driven Phase Separation in the Material Point Method
- Volume-Preserving LBM-MPM Coupling for Air-Water-Sand Mixtures
- A Nonlocal Monolithic Variational Framework for Free Surface Flows
- Stochastic geomorphological transport for terrain erosion simulationHonorable Mention
- Mixwell: Sharp 2D Fluid Brushes for Progressive Physics-Based MixingBest Paper
Computational Photography
- Guidestar-Free Adaptive Optics with Asymmetric Apertures
- MAROON: A Dataset for the Joint Characterization of Near-Field High-Resolution Radio-Frequency and Optical Depth Imaging Techniques
- Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering
- Broadband Hyperspectral 3D Imaging using Dispersed Structured Light
- GenPIE: A Time-Resolved Plenoptic Imager
- Policy-based Foveated Imaging and Perception
Light Transport
- 8DNA: 8D Neural Asset Light Transport by Distribution Learning
- A Generalizable Light Transport 3D Embedding for Global Illumination
- Rao-Blackwellized Markov chain Monte Carlo Light Transport
- Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings
- Photons × Force: Differentiable Radiation Pressure ModelingHonorable Mention
- Differentiable Neutron Transport
Motion Generation, Warping & Control
- GPC: Large-Scale Generative Pretraining for Transferable Motor Control
- SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
- MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
- Deep Motion Warping via Phase-Conditioned Diffusion Autoencoder
- MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance
- Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Parametric Surfaces
- A Robust and Efficient Intersection Algorithm for NURBS Surfaces: Handling Small Loops and Tangent Intersections
- Stress-Aware Panelization of Freeform Surfaces
- Free-form Surface Approximation Using Rotational Patches
- Continuity-Enhancing Degree Elevation and Splits
- NeuPPS: Neural Piecewise Parametric Surfaces
- NeuBase: Spline Surfaces with Neural Basis Functions
Wednesday, 22 July
Efficient Sampling: ReSTIR and More
- Spatio-Temporal Control Variates with ReSTIR for Real-Time RenderingHonorable Mention
- ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling
- ReSTIR BDPT: Bidirectional ReSTIR Path Tracing with Caustics
- Real-Time Level-of-Detail rendering with ReSTIR
- Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion
- Forget Superresolution, Sample Adaptively (when Path Tracing)
Hair, Fur & Feathers
- HairGPT: A Unified Autoregressive Framework for 3D Realistic Hairstyle Synthesis
- HairLRM: Strand-based Hair Modeling via Large Reconstruction Models
- HairPort: In-context 3D-aware Hair Import and Transfer for Images
- Curvature Space Editing of Highly-Coiled Hair
- Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation
Image Generation
- On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
- BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer
- Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
- Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative ExplorationHonorable Mention
- Canvas-to-Image: Compositional Image Generation with Multimodal Controls
- ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
Motion Transfer & Inbetweening
- Motion4Motion: Motion Transfer Across Subjects at Inference
- STyMo: Fast and Controllable Few-Shot Motion Style Transfer
- Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
- ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
- Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation
- LayerInbetween: Occlusion-Aware Stroke Correspondence and Inbetweening with Automatic Layering
Affine Bodies, Shells & Rods
- M-ABD: Scalable, Efficient, and Robust Multi-Affine-Body Dynamics
- Heterogeneous Subspace Corrections for GPU Deformable Multibody Dynamics
- Distributed Affine Body Dynamics with Adaptive Consensus
- Better Bending: Analysis, Construction and Verification of Discrete Bending Models for Kirchhoff-Love Shells
- Efficient B-Spline Finite Elements for Cloth Simulation
- Interactive Yarn-level Knitwear with Nested Douglas-Rachford Splitting
- SymX: Energy-based Simulation from Symbolic Expressions
Reconstruction
- Surface Reconstruction from Unoriented Points via Green’s 3rd Identity
- A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry
- CaRaFe: Camera-Radar Radiance Fields for Scene Reconstruction
- Pixels2Peaks: Converting Terrain Images to Heightmaps
- MegaNorm: Local Patches Embedding for Efficient and Robust Point Normal Orientation at Super-Large Scale
- Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids
- ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
Reconstruction & Sampling
- Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
- Distance Field Rasterization for End-to-End Mesh Reconstruction
- Topology Type Estimation of Simulated 4D Image Data by Combining Downscaling and Convolutional Neural Networks
- NILE: Nested Interleaving of Low-Dimensional Elements
- Gradient-based Design of Non-Uniform Low-Discrepancy Samples
- Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding
- Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras
Vectors Graphics, Strokes & Sketches
- Robust Planar Maps for 3D VectorizationBest Paper
- 2D Gaussian Splatting for Bézier Spline Line Art Vectorization
- Monte Carlo Rendering of Biharmonic Diffusion Curves
- Real-Time GPU Vector Graphics SDF Generation Based on Quadratic Stroke Rendering
- Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching
- NeuralSketch2Surf: Fast Neural Surfacing of Unoriented 3D Sketches
- Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects
4D Humans
- Implicit Surface Compression -- with Good Old Discrete Cosine Transform and Motion Compensation
- 4D Human-Scene Reconstruction from Low-Overlap Captures
- ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
- VFAvatar: Feed-Forward 3D Avatar Reconstruction from Casual Image Collections
- High-Fidelity 4D Cloth Capture Pipeline with a Two-Level Pattern
Differentiable Geometry Processing & Flow Maps
- Iskra: A System for Inverse Geometry Processing
- SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability
- Schrödinger Bridges on Discretized Geometric Domains
- Explicit flows for implicit surfaces
- A Few-Step Generative Model on Cumulative Flow Maps
- Generative Modeling with Orbit-Space Particle Flow Matching
Film/VFX Production
- BodyReLux: Temporally Consistent Full-Body Video Relighting
- Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
- EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation
- LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
- Autoregressive Modeling of Film with Applications in Video Montage
Shading, Relighting and Volumes
- Relit-LiVE: Relight Video by Jointly Learning Environment Video
- GR3EN: Generative Relighting for 3D Environments
- Taming optimization variance in compact neural shading networks
- Multi-feature Radiance Baking Neural Networks for Instant Volumetric Rendering
- Bounding Stratified Bernoulli Impulses for Ray Marching Gaussian Process Implicit Surfaces
- Adaptive Ray Marching for Rendering Gaussian Process Implicit Surfaces
Numerical Methods for Geometry Processing
- MeshFEM: A Block-accelerated Solver for Nonlinear Finite Elements
- Fast Sparse Matrix Permutation for Mesh-Based Direct Solvers
- Statistical Gradient Filtering for Geometry Optimization Under Limited Observations
- GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization
- Robust Biharmonic Skinning Using Geometric Fields
- JGS2-GQ: Training-free 2nd Jacobi with Gaussian Quadrature
Perception
- Dichoptic Foveation
- Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
- Dynamic Visual Dominance in Stereoscopic Foveation
- A Two-Millisecond Passthrough Headset for Perceptual StudiesHonorable Mention
- StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
- Quantifying reality of ultra-realistic 3-D displays - the effect of resolution and contrast
- It’s Not Just a Phase: Creating Phase-Aligned Peripheral Metamers
VR, Haptics & Hardware
- Role-Aware Virtual Agents for Navigational Interaction guided by a Multimodal Large Language Model
- EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering
- Voronoi Rooms: Dynamic Visibility Modulation of Overlapping Spaces for Telepresence
- Atmospheric Haptics: Rendering Airflow and Temperature as Tactile Fields for Interactive Experiences in Virtual Reality
- Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
- Generalized Aberrations for Processing-Aware Optical Design
Walk This Way: Monte Carlo Geometry
- Probe-based Walk on Spheres for Efficient Path Reusing
- Gradient Domain Reconstruction for Monte Carlo PDE SolversHonorable Mention
- Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions
- Walk on Decomposed Subdomains: A Hybrid Monte Carlo–Deterministic Solver for Elliptic PDEsBest Paper
- Walking on Spheres and Talking to Neighbors: Variance Reduction for Laplace's Equation
- Neural Quadrature Rule and Autoregressive Adaptive Sampling
Thursday, 23 July
Inverse Rendering
- Inverse Rendering for Discrete X-Ray Computed TomographyBest Paper
- Ambient-robust Inverse Rendering using Robot-assisted RGB-NIR Imaging
- EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing
- Radiance Caching for Differentiable Path Tracing
- Sample Matching for Joint Extinction Gradient Estimation in Differentiable Volume RenderingHonorable Mention
- Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation
NPR, Style & Abstraction
- Lifting Lines and Tone: Image-Space Stylization in Path-Space
- Abstraction in Style: Beyond Texture and Color
- Progressive Photorealistic Simplification
- GimmBO: Interactive Generative Image Model Merging via Bayesian OptimizationBest Paper
- Semantic-Structural Alignment for Generative Pictorial Charts
- Gradient Descent in the ALPS: Abstracted Low-Poly Stylization and Fabrication
Preventing Collision
- Divide and Truncate: A Penetration and Inversion Free Framework for Coupled Multi-physics System
- Robust and Efficient Penetration-Free Elastodynamics without Barriers
- High-Order Continuous Geometrical Validity
- Floating-Point Robustness in Parametric Surface Continuous Collision Detection: From Algorithm to Benchmarking
- AGIPC: Adaptive In-Solve Algebraic Coarsening for GPU IPC
- YASPS: A Symbolic Framework for Extensible, High-Performance IPC Simulation
Quads & Singularities
- Constant Mean Curvature Surfaces from Discrete Harmonic Maps
- Synchronizing Fields with Singularities
- Global Discrete Optimization for Quad-Dominant Mesh Reduction
- SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields
- Surface Power Diagrams for Knit Singularity Placement
- Learning Sparse Singularities for Cross Field Design
Computational Design
- Co-Optimization of Structure and Manufacturable Semi-Continuous Layers for Laminated Composites
- Diceplay: A Modular Canvas for Physical Image Composition
- A Unified Homogenization Framework for Straight- and Curved-Crease Origami Materials
- mpcGear: Multi-Point Conjugation Gear Mechanisms
- Kinematic Kitbashing
- Computational Design of Coordinate-Motion Assemblies
- Computational Design of Terrestrial Robots with Anisotropic Friction
Geometry Processing
- Exact predicates, exact constructions and combinatorics for mesh CSG
- Surface chamfering for robust tetrahedral meshing
- DJM: Compact Base Meshes for Displacement Mapping using Triangle Jacobians
- Feature-Preserving Offset Meshing
- PR-Cage: Progressive Feasibility Relaxation for Tight Bounding Cage Generation
- C^0 Generalized Coons Volumes over Arbitrary Polyhedra
- Texture-Aware Remeshing for Texture-aware Geometry Processing
Image Editing
- BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing
- ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization
- Continuous Control of Editing Models via Adaptive-Origin Guidance
- HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
- LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
- MAOAM: Unified Object and Material Selection with Vision-Language Models
Simulation
- Progressing Level-of-Detail Animation for Volumetric Elastodynamics
- Mixed Material Point Methods for Stiff Elastoplasticity
- MPM Lite: Linear Kernels and Integration without Particles
- Tube Maps: Fast SPH Boundary Handling with Tubular Coordinates
- Low-Rank Koopman Deformables with Log-Linear Time Integration
- Physics-Inspired Procedural Texturing of Extremely Deformable Surfaces
- Woodstock: Interactive Modeling of Fungal Wood Decay
3D Gaussian Splatting II
- Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting under Uncertainty
- Object-Space Analysis of Local Contrast Sensitivity for Hierarchical Representations of 3D Gaussians
- Learning View-Dependent Splatting Kernels
- CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation
- Radiance Fields from Photons
- Ref-DGS: Reflective Dual Gaussian Splatting
Garments
- LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending
- PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
- Garment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing
- Learning Sewing Patterns via Latent Flow Matching of Implicit Fields
- Learned Universal Interoperable Virtual Try-ON
- FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Imaging, Video, and HDR
- Adapting Quality Metrics to Tone Mapping
- LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography
- Lucky High Dynamic Range Smartphone Imaging
- Soft Anisotropic Diagrams for Differentiable Image Representation
- Single-shot HDR using conventional image sensor shutter functions and optical randomization
- Finding Fast Filters
Learning in Motion
- R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
- TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
- Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
- MUSIC: Learning Muscle-Driven Dexterous Hand Control
- MOCHI: Motion Enhancement of Collaborative Human-object Interactions
- ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies
Gaussian Reconstruction
- GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
- VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
- Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency
- MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization
- RaDe-GS: Rasterizing Depth in Gaussian Splatting
Mapping, Untangling & Summarizing Surfaces
- Implicit Minimal Surfaces for Bijective CorrespondencesHonorable Mention
- Untangling Surfaces via Shape and Mesh Repulsion
- Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axes
- Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence
- Persistence-guided Prescribed Topological Simplification
Multimodal Learning
- PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-Thought
- Reciprocal Latent Fields for Precomputed Sound Propagation
- MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation
- Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
- Just-Dub-It: Video dubbing via Joint Audio-Visual Diffusion
- VfxDB: A Visual Effects Volume Dataset and Benchmark for VDB-Native Generative Modeling