Related papers: Zero-Shot Unsupervised and Text-Based Audio Editin…
Audio editing plays a central role in VR/AR immersion, virtual conferencing, sound design, and other interactive media. However, recent generative audio editing models depend on template-like instruction formats and are restricted to…
Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve the problem by using…
Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling and allow for an intuitive and powerful user interface to drive the image generation process. Expressing spatial…
We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species…
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling…
Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of…
Current strategies for achieving fine-grained prosody control in speech synthesis entail extracting additional style embeddings or adopting more complex architectures. To enable zero-shot application of pretrained text-to-speech (TTS)…
Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work…
Machines that can represent and describe environmental soundscapes have practical potential, e.g., for audio tagging and captioning systems. Prevailing learning paradigms have been relying on parallel audio-text data, which is, however,…
Many problems in image processing and computer vision (e.g. colorization, style transfer) can be posed as 'manipulating' an input image into a corresponding output image given a user-specified guiding signal. A holy-grail solution towards…
We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using…
Image-driven video editing aims to propagate edit contents from the modified first frame to the remaining frames. Existing methods usually invert the source video to noise using a pre-trained image-to-video (I2V) model and then guide the…
State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…
We introduce Delta Denoising Score (DDS), a novel scoring function for text-based image editing that guides minimal modifications of an input image towards the content described in a target prompt. DDS leverages the rich generative prior of…
Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is drinking water."). Existing TI2V frameworks often require…
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but…
Recently, text-to-image diffusion models become a new paradigm in image processing fields, including content generation, image restoration and image-to-image translation. Given a target prompt, Denoising Diffusion Probabilistic Models…
Deep learning-based semantic segmentation models achieve impressive results yet remain limited in handling distribution shifts between training and test data. In this paper, we present SDGPA (Synthetic Data Generation and Progressive…
Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse…
Denoising diffusion probabilistic models (DDPMs) employ a sequence of white Gaussian noise samples to generate an image. In analogy with GANs, those noise maps could be considered as the latent code associated with the generated image.…