Search Results for author:
Found 8 papers, 5 papers with code
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
Global visual geolocation predicts where an image was captured on Earth.
Ranked #1 on
Photo geolocation estimation
on OpenStreetView-5M
PoM: Efficient Image and Video Generation with the Polynomial Mixer
To alleviate this problem, we propose a drop-in replacement for MHA called the Polynomial Mixer (PoM) that has the benefit of encoding the entire sequence into an explicit state.
E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness
dataset, we propose a diffusion-based approach, named DIRECTOR, which generates complex camera trajectories from textual captions that describe the relation and synchronisation between the camera and characters.
Ranked #1 on
3D Generation
on E.T. the Exceptional Trajectories
Don't drop your samples! Coherence-aware training benefits Conditional diffusion
We then condition the diffusion model on both the conditional information and the coherence score.
OpenStreetView-5M: The Many Roads to Global Visual Geolocation
Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms.
Ranked #2 on
Photo geolocation estimation
on OpenStreetView-5M
Analysis of Classifier-Free Guidance Weight Schedulers
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models.
Machine Learning for Brain Disorders: Transformers and Visual Transformers
For image classification, the most common Transformer Architecture uses only the Transformer Encoder in order to transform the various input tokens.
SCAM! Transferring humans between images with Semantic Cross Attention Modulation
In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details.
Ranked #1 on
Pose Transfer
on CelebAMask-HQ
