Dragdiffusion Cvpr 2024 Highlight

This video presents our

[CVPR 2024 Highlight] Compact 3D Gaussian Representation for Radiance Field

Introduction for the

[CVPR 2026 Highlight] Dark3R: Learning Structure from Motion in the Dark

Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to ...

Style Injection in Diffusion (CVPR 2024)

Paper: https://arxiv.org/abs/2404.01051 Personal Website: https://lingeng.foo/ Twitter: https://twitter.com/LinGengFoo.

Presentation Video for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (

[CVPR 2024] Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization

Neural Radiance Fields (NeRFs) have shown great potential in novel view synthesis. However, they struggle to render sharp ...

A universal transferring framework for diffusion models to generate 3D properties, segmentation, and intrinsic images. Project ...

Project Page: https://xjiangan.github.io/glace Code: https://github.com/cvg/glace Timeline: 00:00 Start 00:15 Visual Localization ...

[CVPR 2024] Streaming Dense Video Captioning

CVPR2024- WGSR Paper: Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better ...

[CVPR 2026] Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers

Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios Zhipeng Sui, ...

CVPR 2024

More info: http://nikhilbehari.com/denali.