3D Generation

Particulate: Feed-Forward 3D Object Articulation CVPR 2026 PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing CVPR 2026 PerpetualWonder: Long-horizon Action-conditioned 4D Scene Generation CVPR 2026 Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement CVPR 2026 PhysGaia: A Physics-aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis CVPR 2026 PhysGen: Physically Grounded 3D Shape Generation for Industrial Design CVPR 2026 PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis CVPR 2026 PhysHead: Simulation-Ready Gaussian Head Avatars CVPR 2026 PhysHO: Physics-Based Dynamic 3D Gaussian Human and Object from Monocular Video CVPR 2026 Physically Inspired Gaussian Splatting for HDR Novel View Synthesis CVPR 2026 PhysIR-Splat: Physically Consistent Thermal Infrared Radiative Transfer in 3D Gaussian Splatting CVPR 2026 PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image CVPR 2026 PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction CVPR 2026 PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction CVPR 2026 Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors CVPR 2026 PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes CVPR 2026 PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation CVPR 2026 PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes CVPR 2026 ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars CVPR 2026 Property-Informed Diffusion-Based Text-to-Microstructure Generation CVPR 2026 Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning CVPR 2026 REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting CVPR 2026 Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning CVPR 2026 ReGenHOI: Unifying Reconstruction and Generation for 3D Human-Object Interaction Understanding CVPR 2026 Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence CVPR 2026