Latest Research in Generative Adversarial Networks and Image Synthesis
28 research papers · 2026 median publication year
Top Research Topics in Generative Adversarial Networks and Image Synthesis
- Computer Vision and Pattern Recognition — 24 papers
- Robotics — 2 papers
- Graphics — 1 papers
- Generative Adversarial Networks and Image Synthesis — 1 papers
Highest-Cited Papers
- OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots
- IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis
- PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
- KaiNinja: Extending Native 3D Generators to the Part Level
- DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming
- PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
- SAM3D-Part: Interactive Part Selection and Generation from 3D Objects
- Racing in Volume with Flow Ensembles
- AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
- Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
- Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction
- EdMCGS: Event-Driven Markov Chain Gaussian Splatting for Extreme-Low-Frame-Rate Dynamic Scene Reconstruction
- WorldSculpt: Generating Compositional Worlds from Grounded Videos
- Generalizable 6D Pose Estimation of Textureless Objects with Planar-based Gaussian Splatting
- Joint-Conditioned Stereo Surface Reasoning for Interaction Field Estimation
- HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images
- Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion
- PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation