← Generation
Computer Vision › Generation ›

Image Generation

4128 directly classified papers

Papers per year

Papers

PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud ACL 2024
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines ACL 2024
Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks ACL 2024
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion EMNLP 2024
Accelerating Diffusion Sampling with Optimized Time Steps CVPR 2024
CAGE: Controllable Articulation GEneration CVPR 2024
LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes CVPR 2024
Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data CVPR 2024
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction CVPR 2024
Generalizable Novel-View Synthesis using a Stereo Camera CVPR 2024
Free3D: Consistent Novel View Synthesis without 3D Representation CVPR 2024
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation CVPR 2024
SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors CVPR 2024
Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning CVPR 2024
Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval CVPR 2024
Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields CVPR 2024
Generative Proxemics: A Prior for 3D Social Interaction from Images CVPR 2024
Gaussian Shadow Casting for Neural Characters CVPR 2024
HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data CVPR 2024
Towards Text-guided 3D Scene Composition CVPR 2024
CoGS: Controllable Gaussian Splatting CVPR 2024
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis CVPR 2024
DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation CVPR 2024
SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion CVPR 2024
Boosting Flow-based Generative Super-Resolution Models via Learned Prior CVPR 2024