SIGGRAPH Asia 2025 papers on the web

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

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

March 7 2026

• Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting (SIG)
• Rigidity-Aware 3D Gaussian Deformation from a Single Image (SIG)
• Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction (SIG)
• TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores (SIG)
• DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting (SIG)
• Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation (SIG)
• Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Volumetric Performance Captures (SIG)
• Proteus-ID: ID-Consistent and Motion-Coherent Video Customization (SIG)
• DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning (SIG)
• HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling (SIG)
• Learning Human Motion with Temporally Conditional Mamba (SIG)
• SRBTrack: Terrain-Adaptive Tracking of a Single-Rigid-Body Character Using Momentum-Mapped Space-Time Optimization (SIG)
• Uni-Inter Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts (SIG)
• CHOICE: Coordinated Human-Object Interaction in Cluttered Environments for Pick-and-Place Actions (TOG)
• Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes (SIG)
• MATStruct: High-quality Medial Mesh Computation via Structure-aware Variational Optimization (SIG)
• Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees (SIG)
• Design for Descent: What Makes a Shape Grammar Easy to Optimize? (SIG)
• LVT: Large-Scale Scene Reconstruction via Local View Transformers (SIG)
• CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians (SIG)
• GSWT: Gaussian Splatting Wang Tiles (SIG)
• Spectral-GS: Taming 3D Gaussian Splatting with Spectral Entropy (SIG)
• A compact stochastic representation for Monte Carlo Path Traced images (SIG)
• BlobCtrl: Taming Controllable Blob for Element-level Image Editing (SIG)
• ConsistEdit: Highly Consistent and Precise Training-free Visual Editing (SIG)
• Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off (SIG)
• DreamO: A Unified Framework for Image Customization (SIG)
• The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion (SIG)
• Closed-form Cauchy Coordinates and Their Derivatives for 2D High-order Cages (SIG)
• Aerial Path Planning for Urban Geometry and Texture Co-Capture (SIG/TOG)
• Direct Rendering of Intrinsic Triangulations (TOG)

March 6 2026

• Multiphase Particle-Based Simulation of Poro-Elasto-Capillary Effects (SIG)
• Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images (SIG)
• AniTex: Light-Geometry Consistent PBR Material Generation for Animatable Objects (SIG)
• FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion (SIG)
• Generating Objects with Part-Articulation from a Single Image (SIG)
• LARM: A Large Articulated Object Reconstruction Model (SIG)
• ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents (SIG)
• Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion (SIG)
• LLM-Primitives: Large Language Model for 3D Reconstruction with Primitives (SIG)
• ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation (SIG/TOG)
• Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models (SIG)
• PractiLight: Practical Light Control Using Foundational Diffusion Models (SIG/TOG)
• Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos (TOG)
• Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA (SIG)
• B4M: Breaking Low-Rank Adapter for Making Content-Style Customization (TOG)
• In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation (SIG)

March 5 2026

• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views (SIG/TOG)
• PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems (SIG)
• Underwater Optical Backscatter Communications using Acousto-Optic Beam Steering (SIG/TOG)
• Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light (SIG)
• Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding (SIG)
• Transient LASSO: Transient Large-Scale Scene Reconstruction (SIG)
• Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation (SIG/TOG)
• Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search (SIG)
• StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance (SIG)
• Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion (SIG)
• Motion2Motion: Cross-topology Motion Retargeting with Sparse Correspondence (SIG/TOG)
• Generating Detailed Character Motion from Blocking Poses (SIG)
• MaskedManipulator: Versatile Whole-Body Manipulation (SIG)
• The Granule-In-Cell Method for Simulating Sand-Water Mixtures (SIG/TOG)
• Implicit Incompressible Porous Flow using SPH (SIG/TOG)

March 4 2026

• Robust Derivative Estimation with Walk on Stars (SIG/TOG)
• Off-Centered WoS-Type Solvers with Statistical Weighting (SIG)
• An Adjoint Method for Differentiable Fluid Simulation on Flow Maps (SIG)
• Efficient and Scalable Spatial Regularization of Optimal Transport (SIG)
• Medial Sphere Preconditioning for Knot Untangling and Volume-Filling Curves (SIG)
• Lifted Surfacing of Generalized Sweep Volumes (SIG/TOG)
• RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction (TOG)
• Convection Augmented Gauss Reconstruction for Unoriented Point Clouds (SIG/TOG)
• MODepth: Benchmarking Mobile Multi-frame Monocular Depth Estimation with Optical Image Stabilization (SIG)
• From Rigging to Waving: 3D-Guided Diffusion for Natural Animation of Hand-Drawn Characters (SIG/TOG)
• Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction (SIG)
• AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models (SIG)
• Animus3D: Text-driven 3D Animation via Motion Score Distillation (SIG)
• X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents (SIG)
• FairyGen: Storied Cartoon Video from a Single Child-Drawn Character (SIG)

March 3 2026

• SS4D: Native 4D Generative Model via Structured Spacetime Latents (SIG/TOG)
• PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion (SIG)
• Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation (SIG/TOG)
• Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents (SIG)
• How Does a Virtual Agent Decide Where to Look? Symbolic Cognitive Reasoning for Embodied Head Rotation (SIG)
• SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis (SIG)
• JoruriPuppet: Learning Tempo-Changing Mechanisms Beyond the Beat for Music-to-Motion Generation with Expressive Metrics (SIG)
• PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos (SIG)
• Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture (SIG/TOG)
• GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes (SIG)
• Neural Hamiltonian Deformation Fields for Dynamic Scene Rendering (SIG)
• MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars (SIG)
• MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis (SIG)
• Jump Restore Light Transport (SIG/TOG)
• Gaussian Integral Linear Operators for Precomputed Graphics (SIG/TOG)

March 2 2026

• ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation (SIG)
• PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples (SIG)
• AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping (SIG)
• MALeR: Improving Compositional Fidelity in Layout-Guided Generation (SIG/TOG)
• One String to Pull Them All: Fast Assembly of Curved Structures from Flat Auxetic Linkages (SIG/TOG)
• Discovering Folding Lines for Surface Compression (SIG)
• Snapping Deployable Toroids for Modular Gridshells (SIG/TOG)
• Star-Shaped Distance Voronoi Diagrams for 3D Metamaterial Design (SIG)
• Strands2Cards: Automatic Generation of Hair Cards from Strands (SIG/TOG)
• Shaping Strands with Neural Style Transfer (SIG/TOG)
• CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling (SIG)
• Single-Shot Facial Capture using Polarized RGB Sinusoidal Illumination (SIG)
• 3DPR: Single Image 3D Portrait Relighting with Generative Priors (SIG)
• Acoustic Reliefs (SIG/TOG)
• PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models (SIG)

March 1 2026

• $G^2$ Interpolating Spline with Local Maximum Curvature (SIG/TOG)
• Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization (SIG)
• Curvature Enthusiasm: Correspondence-Free Interpolation and Matching of Articulated 3D Shapes using Compressed Normal Cycles (SIG/TOG)
• Control Operators for Interactive Character Animation (SIG/TOG)
• Environment-aware Motion Matching (SIG/TOG)
• StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data (SIG)
• Physics-Based Motion Imitation with Adversarial Differential Discriminators (SIG)
• Low-Rank Adaptation of Neural Fields (SIG)
• Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes (SIG/TOG)
• SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction (SIG)
• RaRa Clipper: A Clipper for Gaussian Splatting Based on Ray Tracer and Rasterizer (SIG)
• LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization (SIG)
• Neural Image abstraction using long smoothing B-splines (SIG/TOG)
• UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images (SIG)
• Object-level Visual Prompts for Compositional Image Generation (SIG)

February 28 2026

• GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats (SIG)
• Artifact-Resilient Real-Time Holography (SIG/TOG)
• TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction (SIG)
• Clustered Error Correction with Grouped 4D Gaussian Splatting (SIG)
• Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video (SIG)
• 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture (SIG)
• Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation (SIG/TOG)
• Numerical Homogenization of Sand from Grain-level Simulations (SIG/TOG)
• Improving Curl Noise (SIG)
• Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video (SIG)
• AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation (SIG)
• Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors (SIG/TOG)
• Neighbor-Aware Data-Driven Relaxation of Stitch Mesh Models for Knits (SIG)
• AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry (SIG)
• Overlap Region Extraction of Two NURBS Surfaces (SIG/TOG)

February 27 2026

• SZ Sequences: Binary-Constructed $(0, 2^q)$-Sequences (SIG/TOG)
• Adaptive Neural Kernels for Gradient-domain Rendering (SIG)
• ShapeGen: Towards High-Quality 3D Shape Synthesis (SIG)
• OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion (SIG)
• SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation (SIG)
• DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model (SIG)
• ELAD: Blind Face Restoration using Expectation-based Likelihood Approximation and Diffusion Prior (SIG)
• Supra-threshold Contrast Perception in Augmented Reality (SIG)
• Modeling and Exploiting the Time Course of Chromatic Adaptation for Display Power Optimizations in Virtual Reality (SIG/TOG)
• Performance Analysis of Catch-Up Eye Movements in Visual Tracking (SIG)
• Glare Pattern Depiction: High-Fidelity Physical Computation and Physiologically-Inspired Visual Response (SIG/TOG)
• MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization (SIG/TOG)
• EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly (SIG)
• Inverse Radiative Transport for Infrared Scenes with Gaussian Primitives (SIG)
• WATER: Watertight Tessellation for Real-Time Pixel-Accurate Rendering of Large-Scale Surfaces (SIG/TOG)

February 26 2026

• High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation (SIG)
• Audio-Driven Universal Gaussian Head Avatars (SIG)
• ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model (SIG)
• X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio (SIG)
• LEGO-Maker: Autoregressive Image-Conditioned LEGO Model Creation (SIG/TOG)
• LegoACE: Autoregressive Construction Engine for Expressive LEGO Assemblies (SIG)
• Computational Design of Shape-Aware Sieves (SIG)
• Designing with Tension: Nearly-Developable Patch Layouts (SIG)
• Fabricable Discretized Ruled Surfaces (TOG)
• DiffCamera: Arbitrary Refocusing on Images (SIG)
• Learning to Refocus with Video Diffusion Models (SIG)
• Generating the Past, Present and Future from a Motion-Blurred Image (SIG/TOG)
• Automated Design of Compound Lenses with Discrete-Continuous Optimization (SIG)
• UltraZoom: Generating Gigapixel Images from Regular Photos (SIG)
• Nonlinear Noise2Noise for Efficient Monte Carlo Denoiser Training (SIG)

January 30, 2026

• InfiniHuman: Realistic 3D Human Creation with Precise Control (SIG)
• HRM^2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans (SIG)
• Constructing Diffusion Avatar with Learnable Embeddings (SIG)
• HumanLift: Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement (SIG)
• PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image (SIG)
• Fast & Stable Control of Coupled Solid-Fluid Dynamic Systems (SIG)
• Force-Dual Modes: Subspace Design from Stochastic Forces (SIG/TOG)
• Can Any Model Be Fabricated? Inverse Operation Based Planning for Hybrid Additive–Subtractive Manufacturing (SIG/TOG)
• MiGumi: Making Tightly Coupled Integral Joints Millable (SIG/TOG)
• Curve-Based Slicer for Multi-Axis DLP 3D Printing (SIG/TOG)
• INF-3DP: Implicit Neural Fields for Collision-Free Multi-Axis 3D Printing (SIG/TOG)
• NeuralPVS: Learned Estimation of Potentially Visible Sets (SIG)
• PatchEX: High-Quality Real-Time Temporal Supersampling through Patch-based Parallel Extrapolation (TOG)
• Audio Driven Real-Time Facial Animation for Social Telepresence (SIG)
• LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation (SIG)

January 29, 2026

• Fine-Grained Spatially Varying Material Selection in Images (SIG/TOG)
• S3 Imagery: Specular Shading from Scratch-Anisotropy (SIG)
• Neural Octahedral Field: Octahedral Prior for Simultaneous Smoothing and Sharp Edge Regularization (SIG/TOG)
• SeqTex: Generate Mesh Textures in Video Sequence (SIG)
• Simplifying Textured Triangle Meshes in the Wild (SIG/TOG)
• Solid-Shell Labeling for Discrete Surfaces (SIG)
• LookUp3D: Data-Driven 3D Scanning (SIG)
• Computational Modeling and Design of Capacitive Stretch Sensors (SIG/TOG)
• PartUV: Part-Based UV Unwrapping of 3D Meshes (SIG)
• Local Surface Parameterizations via Smoothed Geodesic Splines (TOG)
• RibbonSculpt: Voronoi Ball based 3D Sculpting from Sparse VR Ribbons (SIG)
• Precise Gradient Discontinuities in Neural Fields for Subspace Physics (SIG)
• Variational Neural Surfacing of 3D Sketches (SIG)
• Neural Kinematic Bases for Fluids (SIG)
• Generative Head-Mounted Camera Captures for Photorealistic Avatars (SIG/TOG)

January 10, 2026

• Frame-Free Representation of Polarized Light for Resolving Stokes Vector Singularities (SIG/TOG)
• Viscous Vortex Dynamics on Surfaces (SIG/TOG)
• Fast Galerkin Multigrid Method for Unstructured Meshes (SIG/TOG)
• Reliable Iterative Dynamics: A Versatile Method for Fast and Robust Simulation (TOG)
• Implicit Position-Based Fluids (SIG)
• Implicit Bonded Discrete Element Method with Manifold Optimization (TOG)
• Shape-for-Motion: Precise and Consistent Video Editing With 3D Proxy (SIG)
• Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval (SIG)
• CamCloneMaster: Enabling Reference-based Camera Control for Video Generation (SIG)
• Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation (SIG)
• Cut2Next: Generating Next Shot via In-Context Tuning (SIG)
• CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion (SIG)
• Scattering-Aware Color Calibration for 3D Printers Using a Simple Calibration Target (SIG/TOG)
• Example-Based Feature Painting on Textures (SIG/TOG)
• DiffTex: Differentiable Texturing for Architectural Proxy Models (SIG/TOG)

January 8, 2026

• RCTrans: Transparent Object Reconstruction in Natural Scene via Refractive Correspondence Estimation (SIG)
• Sparse SVBRDF Acquisition via Importance-Aware Illumination Multiplexing (SIG/TOG)
• EBREnv: SVBRDF Estimation in Uncontrolled Environment Lighting via Exemplar-Based Representation (SIG)
• Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos (SIG)
• Surface-Aware Distilled 3D Semantic Features (SIG)
• Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes (SIG)
• PoissonNet: A Local-Global Approach for Learning on Surfaces (SIG/TOG)
• Navigating with Annealing Guidance Scale in Diffusion Space (SIG)
• Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation (SIG)
• OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models (SIG)
• STGlight: Online Indoor Lighting Estimation via Spatio-Temporal Gaussian Fusion (SIG/TOG)
• GenLit: Reformulating Single-Image Relighting as Video Generation (SIG)
• DynVFX: Augmenting Real Videos with Dynamic Content (SIG)
• Vertex Features for Neural Global Illumination (SIG)
• GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction (TOG)

December 18, 2025

• SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes (SIG/TOG)
• Capturing Non-Linear Human Perspective in Line Drawings (SIG)
• NeuVAS: Neural Implicit Surfaces for Variational Shape Modeling (SIG/TOG)
• NESI: Neural Explicit-Shape-Intersection-Based Geometry Representation (TOG)
• Large-Area Fabrication-Aware Computational Diffractive Optics (SIG/TOG)
• ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction (SIG)
• Waste-to-Value: Reutilized Material Maximization for Additive and Subtractive Hybrid Remanufacturing (SIG/TOG)
• Designing and Fabricating Color BRDFs with Differentiable Wave Optics (SIG/TOG)
• Imperfect Image-Space Control Variates for Monte Carlo Rendering (SIG/TOG)
• ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths (SIG)

December 11, 2025

• AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting (SIG)
• Reconfigurable Hinged Kirigami Tessellations (SIG)
• Neural Visibility of Point Sets (SIG)
• CFC: Simulating Character-Fluid Coupling using a Two-Level World Model (SIG/TOG)
• PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction (SIG)
• Harnessing Diffusion-Yielded Score Priors for lmage Restoration (SIG/TOG)
• Learning to Ball: Composing Policies for Long-Horizon Basketball Moves (SIG/TOG)
• ASIA: Adaptive 3D Segmentation using Few Image Annotations (SIG)
• In-2-4D: Inbetweening from Two Single-View Images to 4D Generation (SIG)
• WorldExplorer: Towards Generating Fully Navigable 3D Scenes (SIG)

December 4, 2025

• Hyperspectral Polarimetric BRDFs of Real-world Materials (SIG)
• VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models (SIG)
• Autoregressive Generation of Static and Growing Trees (SIG)
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patches (SIG/TOG)
• MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction (SIG/TOG)
• Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields (SIG)
• Spectral Prefiltering of Neural Fields (SIG)
• Motion In-Betweening for Densely Interacting Characters (SIG)
• ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths (SIG)
• Diffusion-Guided Relighting for Single-Image SVBRDF Estimation (SIG)
• Sample Space Partitioning and Spatiotemporal Resampling for Specular Manifold Sampling (SIG)
• Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction (SIG/TOG)
• Automatic Sampling for Discontinuities in Differentiable Shaders (SIG/TOG)
• DSCombiner: Double Shrinkage for Combining Biased and Unbiased Monte Carlo Renderings (SIG/TOG)

November 27, 2025

• Practical Gaussian process implicit surfaces with sparse convolutions (SIG/TOG)
• Harmonic caching for walk on spheres (SIG/TOG)
• Jackknife Transmittance and MIS Weight Estimation (SIG/TOG)
• Imperfect Image-Space Control Variates for Monte Carlo Rendering (SIG/TOG)
• Evaluating and Sampling Glinty NDFs in Constant Time (SIG/TOG)
• CameraVDP: Perceptual Display Assessment with Uncertainty Estimation via Camera and Visual Difference Prediction (SIG)
• Spectral Reconstruction with Uncertainty Quantification via Differentiable Rendering and Null-Space Sampling (SIG)
• Generating 360 Video is What You Need For a 3D Scene (SIG)
• Many-Worlds Inverse Rendering (SIG/TOG)
• GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling (SIG/TOG)
• Progressive Outfit Assembly and Instantaneous Pose Transfer (SIG)
• Auto Hair Card Extraction for Smooth Hair with Differentiable Rendering (SIG/TOG)
• Kinetic Free-Surface Flows and Foams with Sharp Interfaces (SIG/TOG)
• RL-ACD: Reinforcement Learning-based Approximate Convex Decomposition (SIG/TOG)
• Lightweight, Edge-Aware, and Temporally Consistent Supersampling for Mobile Real-Time Rendering (SIG/TOG)
• Ultrafast and Controllable Online Motion Retargeting for Game Scenarios (SIG/TOG)
• Efficient Object Reconstruction with Differentiable Area Light Shading (SIG)

October 23, 2025

• Statistical Error Reduction for Monte Carlo Rendering (SIG)

October 16, 2025

• BSP-OT: Sparse transport plans between discrete measures in loglinear time (SIG/TOG)
• Fovea Stacking: Imaging with Dynamic Localized Aberration Correction (SIG/TOG)
• Large-Area Fabrication-Aware Computational Diffractive Optics (SIG/TOG)
• Designing and Fabricating Color BRDFs with Differentiable Wave Optics (SIG/TOG)

October 2, 2025

• Inverse Tiling of 2D Finite Domains (SIG)
• Fire-X: Extinguishing Fire with Stoichiometric Heat Release (SIG/TOG)
• NURBS-Based Grid Shell Form finding on Domains with Topologically Arbitrary Boundaries (SIG/TOG)
• Hierarchical Neural Semantic Representation for 3D Semantic Correspondence (SIG)
• FreeMusco: Motion-Free Learning of Latent Control for Morphology-Adaptive Locomotion in Musculoskeletal Characters (SIG)

September 8, 2025

• Chapper: Carvable Hull-and-Pack for Subtractive Manufacturing (SIG/TOG)
• Waste-to-Value: Reutilized Material Maximization for Additive and Subtractive Hybrid Remanufacturing (SIG/TOG)

September 5, 2025

• ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction (SIG)

September 3, 2025

• CrossGen: Learning and Generating Cross Fields for Quad Meshing (SIG/TOG)

August 28, 2025

• AutoSketch: VLM-assisted Style-Aware Vector Sketch Completion (SIG)

August 24, 2025

• SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes (SIG TOG Paper)
• Page published