"Consistency Models. (arXiv:2303.01469v1 [cs.LG])" — A new family of generative models that achieve high sample quality without adversarial training that supports fast one-step generation by design.

Paper: http://arxiv.org/abs/2303.01469

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Samples generated by EDM (top),…

"3D generation on ImageNet. (arXiv:2303.01416v1 [cs.CV])" — A more detailed/accurate method to generate 3D images based on 2D input images.

Paper: http://arxiv.org/abs/2303.01416

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Selected samples from EG3D (Cha…

"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation. (arXiv:2303.01311v1 [cs.CV])" — Generating random game characters simply based on text input instead of customizing a pre-created character's visual attributes.

Paper: http://arxiv.org/abs/2303.01311

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Game characters created by the …

"Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?. (arXiv:2303.01255v1 [cs.CV])" — Would the quality of generative AI tools be affected if the input images are generated by AI tools themselves? An initial (simulated) experiment to explore this question.

Paper: http://arxiv.org/abs/2303.01255

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Two sets of sample images — the…

"X&Fuse: Fusing Visual Information in Text-to-Image Generation. (arXiv:2303.01000v1 [cs.CV])" — Multiple ways to condition images prior to text-to-image generation to achieve better output results.

Paper: http://arxiv.org/abs/2303.01000

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
X&Fuse conditions the model on …

"Scalable Diffusion Models with Transformers. (arXiv:2212.09748v2 [cs.CV] UPDATED)" — Creating diffusion models that use transformers instead UNets.

Paper: http://arxiv.org/abs/2212.09748
Code: https://github.com/facebookresearch/DiT

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Diffusion models with transform…

"Collage Diffusion. (arXiv:2303.00262v1 [cs.CV])" — Creating harmonious and cohesive output images based on a text prompt and a collection of images as input.

Paper: http://arxiv.org/abs/2303.00262

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Collage Diffusion creates globa…

"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing. (arXiv:2303.00137v1 [cs.CV])" — Generating realistic shadows and reflections using 2D images and deep learning techniques.

Paper: http://arxiv.org/abs/2303.00137

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
PixHt-Lab renders realistic ref…

"Magic: Multi Art Genre Intelligent Choreography Dataset and Network for 3D Dance Generation. (arXiv:2212.03741v3 [cs.CV] UPDATED)" — A choreography dataset and a network for generating 3D dance segments based on a music clip as input.

Paper: http://arxiv.org/abs/2212.03741

Note: v3 of the paper is currently not available in PDF form on arXiv.

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A conceptual overview of Magic.…

"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning. (arXiv:2302.14794v1 [cs.CV])" — Rather than using a frozen language model to communicate visual concepts, this method uses a meta -mapper to act as a bridge between large-scale visiona and language models.

Paper: http://arxiv.org/abs/2302.14794

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Multimodal few-shot meta-learni…

"TextIR: A Simple Framework for Text-based Editable Image Restoration. (arXiv:2302.14736v1 [cs.CV])" — Using text input to restore damaged images by specifying how to fill in the damage areas by way of text descriptions.

Paper: http://arxiv.org/abs/2302.14736

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of image restoration r…

"Towards Enhanced Controllability of Diffusion Models. (arXiv:2302.14368v1 [cs.CV])" — Creating a diffusion model that is easier to edit/style based on input images by conditioning the model on a spatial content mask and a flattened style embedding.

Paper: http://arxiv.org/abs/2302.14368

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparison of the proposed mode…

"One-Shot Video Inpainting. (arXiv:2302.14362v1 [cs.CV])" — A method to inpaint videos where instead of having to provide masks for each frame, you only need to provide the object mask for the initial frame in the video sequence.

Paper: http://arxiv.org/abs/2302.14362

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Qualitative comparison between …

"Deep Learning for Identifying Iran's Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM. (arXiv:2302.14354v1 [cs.CV])" — Using machine learning to identify damage and defects to cultural heritage buildings using Convolutional Neural Networks (CNN).

Paper: http://arxiv.org/abs/2302.14354

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparing a picture with small-…

"Accuracy and Fidelity Comparison of Luna and DALL-E 2 Diffusion-Based Image Generation Systems. (arXiv:2301.01914v2 [cs.CV] UPDATED)" — Comparing the accuracy and fidelity of images generated by DALL-E 2 and Luna, which is Stable Diffusion-based.

Paper: http://arxiv.org/abs/2301.01914
Luna code: https://github.com/slowy07/luna

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Selected image samples from the…

"Diffusion Posterior Sampling for General Noisy Inverse Problems. (arXiv:2209.14687v3 [stat.ML] UPDATED)" — Extending diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling.

Paper: http://arxiv.org/abs/2209.14687
Code: https://github.com/dps2022/diffusion-posterior-sampling

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Solving noisy linear, and nonli…

"Subspace Diffusion Generative Models. (arXiv:2205.01490v2 [cs.LG] UPDATED)" — Restricting diffusion via projections onto subspaces to reduce computational time and cost without affecting the overall quality of the generated image.

Paper: http://arxiv.org/abs/2205.01490
Code: https://github.com/bjing2016/subspace-diffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Random high resolution samples …

"Large Scale Visual Food Recognition. (arXiv:2103.16107v3 [cs.CV] UPDATED)" — A food dataset with 2,000 categories and over 1 million images that can be used for food recognition.

Paper: http://arxiv.org/abs/2103.16107
Code: https://github.com/Liuyuxinict/prenet/

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The distributions over each cat…

"Directed Diffusion: Direct Control of Object Placement through Attention Guidance. (arXiv:2302.13153v1 [cs.CV])" — Controlling object placement in diffusion models by way of attention guidance.

Paper: http://arxiv.org/abs/2302.13153

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Directed Diffusion (DD) key res…

"In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages" — Measuring the formality of the generated text for different languages using multilingual generative language models.

Paper: https://arxiv.org/abs/2302.12299

#AI #NewPaper #DeepLearning #MachineLearning #Language

<<Find this useful? Please boost so that others can benefit too 🙂>>
Differences between formal and …