Search Results for author:
Found 35 papers, 17 papers with code
AnyTop: Character Animation Diffusion with Any Topology
Generating motion for arbitrary skeletons is a longstanding challenge in computer graphics, remaining largely unexplored due to the scarcity of diverse datasets and the irregular nature of the data.
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image generation models.
Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects
We propose a generative technique to edit 3D shapes, represented as meshes, NeRFs, or Gaussian Splats, in approximately 3 seconds, without the need for running an SDS type of optimization.
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment.
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
Both approaches lead to improved image quality when compared to monolithic models or generic, prompt-independent workflows.
Masked Extended Attention for Zero-Shot Virtual Try-On In The Wild
The method employs extended attention to transfer image information from reference to target images, overcoming two significant challenges.
V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data
We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content.
Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing?
LCM-Lookahead for Encoder-based Text-to-Image Personalization
In this work, we explore the potential of using such shortcut-mechanisms to guide the personalization of text-to-image models to specific facial identities.
Breathing Life Into Sketches Using Text-to-Video Priors
A sketch is one of the most intuitive and versatile tools humans use to convey their ideas visually.
MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion
We introduce Multi-view Ancestral Sampling (MAS), a method for 3D motion generation, using 2D diffusion models that were trained on motions obtained from in-the-wild videos.
State of the Art on Diffusion Models for Visual Computing
The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes.
OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
Evasion Attacks (EA) are used to test the robustness of trained neural networks by distorting input data to misguide the model into incorrect classifications.
Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis
Building on state-of-the-art diffusion-based music generative models, we introduce performance conditioning - a simple tool indicating the generative model to synthesize music with style and timbre of specific instruments taken from specific performances.
Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts.
Neural Projection Mapping Using Reflectance Fields
We introduce a high resolution spatially adaptive light source, or a projector, into a neural reflectance field that allows to both calibrate the projector and photo realistic light editing.
Human Motion Diffusion as a Generative Prior
We evaluate the composition methods using an off-the-shelf motion diffusion model, and further compare the results to dedicated models trained for these specific tasks.
Ranked #6 on
Motion Synthesis
on Inter-X
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
Specifically, we employ two components: First, an encoder that takes as an input a single image of a target concept from a given domain, e. g. a specific face, and learns to map it into a word-embedding representing the concept.
Single Motion Diffusion
We harness the power of diffusion models and present a denoising network explicitly designed for the task of learning from a single input motion.
OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields
A modest neural network is trained on the input planes to return an inside/outside estimate for a given 3D coordinate, yielding a powerful prior that induces smoothness and self-similarities.
Human Motion Diffusion Model
In this paper, we introduce Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain.
Ranked #1 on
Motion Synthesis
on HumanAct12
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes.
Ranked #7 on
Personalized Image Generation
on DreamBooth
Unaligned Supervision For Automatic Music Transcription in The Wild
In order to overcome data collection barriers, previous AMT approaches attempt to employ musical scores in the form of a digitized version of the same song or piece.
MotionCLIP: Exposing Human Motion Generation to CLIP Space
MotionCLIP gains its unique power by aligning its latent space with that of the Contrastive Language-Image Pre-training (CLIP) model.
State-of-the-Art in the Architecture, Methods and Applications of StyleGAN
Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks.
Self-Conditioned Generative Adversarial Networks for Image Editing
We compare our models to a wide range of latent editing methods, and show that by alleviating the bias they achieve finer semantic control and better identity preservation through a wider range of transformations.
Stitch it in Time: GAN-Based Facial Editing of Real Videos
The ability of Generative Adversarial Networks to encode rich semantics within their latent space has been widely adopted for facial image editing.
Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generators
In addition, we propose training a semantic segmentation network along with the translation task, and to leverage this output as a loss term that improves robustness.
Learned Queries for Efficient Local Attention
Vision Transformers (ViT) serve as powerful vision models.
Ranked #393 on
Image Classification
on ImageNet
HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
In this work, we introduce this approach into the realm of encoder-based inversion.
ClipCap: CLIP Prefix for Image Captioning
Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image.
Ranked #1 on
Image Captioning
on Conceptual Captions
JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
To alleviate this problem, we introduce JOKR - a JOint Keypoint Representation that captures the motion common to both the source and target videos, without requiring any object prior or data collection.
Pivotal Tuning for Latent-based Editing of Real Images
The key idea is pivotal tuning - a brief training process that preserves the editing quality of an in-domain latent region, while changing its portrayed identity and appearance.
MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation
Mesh-based learning is one of the popular approaches nowadays to learn shapes.
Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderer
The long-coveted task of reconstructing 3D geometry from images is still a standing problem.
