Computer Vision › Generation ›

Image Generation

4128 directly classified papers

Papers per year

Papers

Instruction-based Image Editing with Planning, Reasoning, and Generation ICCV 2025

SViM3D: Stable Video Material Diffusion for Single Image 3D Generation ICCV 2025

Fine-Grained 3D Gaussian Head Avatars Modeling from Static Captures via Joint Reconstruction and Registration ICCV 2025

DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors ICCV 2025

WIPES: Wavelet-based Visual Primitives ICCV 2025

StableCodec: Taming One-Step Diffusion for Extreme Image Compression ICCV 2025

Learning Efficient and Generalizable Human Representation with Human Gaussian Model ICCV 2025

UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields ICCV 2025

KV-Edit: Training-Free Image Editing for Precise Background Preservation ICCV 2025

Improving Rectified Flow with Boundary Conditions ICCV 2025

AV-Flow: Transforming Text to Audio-Visual Human-like Interactions ICCV 2025

SEAL: Semantic Aware Image Watermarking ICCV 2025

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling ICCV 2025

Di[M]O: Distilling Masked Diffusion Models into One-step Generator ICCV 2025

SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusion ICCV 2025

Dual-Process Image Generation ICCV 2025

ROAR: Reducing Inversion Error in Generative Image Watermarking ICCV 2025

Tile-wise vs. Image-wise: Random-Tile Loss and Training Paradigm for Gaussian Splatting ICCV 2025

BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis ICCV 2025

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation ICCV 2025

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs ICCV 2025

Sparse Fine-Tuning of Transformers for Generative Tasks ICCV 2025

Inverse Image-Based Rendering for Light Field Generation from Single Images ICCV 2025

Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution ICCV 2025

QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization ICCV 2025