Paper-Conference

👑 CVPR 2026 | Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models featured image

Image Generation

👑 CVPR 2026 | Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models

Qifan Li

• Mar 1, 2026 • 1 min read

👑 CVPR 2026 | IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting featured image

3D Gaussian Splatting

👑 CVPR 2026 | IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting

Wei Long

• Mar 1, 2026 • 1 min read

👑 CVPR 2026 | Guiding a Diffusion Transformer with the Internal Dynamics of Itself featured image

Image Generation

👑 CVPR 2026 | Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Xingyu Zhou

• Mar 1, 2026 • 1 min read

👑 CVPR 2026 | Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression featured image

Image Compression

👑 CVPR 2026 | Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

Shiyin Jiang

• Mar 1, 2026 • 1 min read

Neural Stereo Video Compression with Hybrid Disparity Compensation featured image

Video Compression

Neural Stereo Video Compression with Hybrid Disparity Compensation

Shiyin Jiang

• Oct 1, 2025 • 1 min read

LRTI-VSR: Learning Long-Range Refocused Temporal Information from Short Video Clips featured image

Video Super-Resolution

LRTI-VSR: Learning Long-Range Refocused Temporal Information from Short Video Clips

Xingyu Zhou

• Oct 1, 2025 • 1 min read

Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution featured image

Image Compression

Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution

Minghao Han

• Oct 1, 2025 • 1 min read

👑 CVPR 2026 | Task-Aware Image Signal Processor for Advanced Visual Perception featured image

Image Signal Processor

👑 CVPR 2026 | Task-Aware Image Signal Processor for Advanced Visual Perception

Kai Chen

• Oct 1, 2025 • 1 min read

🏆 ICCVW 2025 | HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancement featured image

Image Enhancement

🏆 ICCVW 2025 | HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancement

Xiaorui Zhao

• Oct 1, 2025 • 1 min read

🏆 ICCV 2025 | PerLDiff：Controllable Street View Synthesis Using Perspective-Layout Diffusion Models featured image

Image Generation

🏆 ICCV 2025 | PerLDiff：Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

Jinhua Zhang

• Oct 1, 2025 • 1 min read