research
∙
09/21/2023
Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis
Generating multi-instrument music from symbolic music representations is...
share
research
∙
07/13/2023
Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
Text-to-image (T2I) personalization allows users to guide the creative i...
research
∙
07/03/2023
ROAR: Robust Adaptive Reconstruction of Shapes Using Planar Projections
The majority of existing large 3D shape datasets contain meshes that len...
research
∙
06/11/2023
Neural Projection Mapping Using Reflectance Fields
We introduce a high resolution spatially adaptive light source, or a pro...
research
∙
03/02/2023
Human Motion Diffusion as a Generative Prior
In recent months, we witness a leap forward as denoising diffusion model...
research
∙
02/23/2023
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
Text-to-image personalization aims to teach a pre-trained diffusion mode...
research
∙
02/12/2023
Single Motion Diffusion
Synthesizing realistic animations of humans, animals, and even imaginary...
research
∙
11/23/2022
OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields
Reconstructing 3D shapes from planar cross-sections is a challenge inspi...
research
∙
09/29/2022
Human Motion Diffusion Model
Natural and expressive human motion generation is the holy grail of comp...
research
∙
08/02/2022
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Text-to-image models offer unprecedented freedom to guide creation throu...
research
∙
04/28/2022
Unaligned Supervision For Automatic Music Transcription in The Wild
Multi-instrument Automatic Music Transcription (AMT), or the decoding of...
research
∙
03/15/2022
MotionCLIP: Exposing Human Motion Generation to CLIP Space
We introduce MotionCLIP, a 3D human motion auto-encoder featuring a late...
research
∙
02/08/2022
Self-Conditioned Generative Adversarial Networks for Image Editing
Generative Adversarial Networks (GANs) are susceptible to bias, learned ...
research
∙
12/30/2021
Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generators
Supervision for image-to-image translation (I2I) tasks is hard to come b...
research
∙
12/21/2021
Learned Queries for Efficient Local Attention
Vision Transformers (ViT) serve as powerful vision models. Unlike convol...
research
∙
05/27/2021
MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation
Mesh-based learning is one of the popular approaches nowadays to learn s...
research
∙
03/26/2019