Related papers: EraseAnything++: Enabling Concept Erasure in Recti…
Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…
Existing video object removal methods predominantly rely on diffusion models following a noise-to-data paradigm, where generation starts from uninformative Gaussian noise. This approach discards the rich structural and contextual priors…
Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…
Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…
Editing images with diffusion models under strict training-free constraints remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they struggle to preserve identity and capture…
We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…
Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to…
Image watermarking supports authenticity and provenance, yet many schemes are still easy to bypass with various distortions and powerful generative edits. Deep learning-based watermarking has improved robustness to diffusion-based image…
Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…
Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…
Generative models, particularly diffusion-based text-to-image (T2I) models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts (e.g., offensive or copyrighted content, or…
Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment,…
Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions…
Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive…
While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…
Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion models by distilling via the diffusion model training…
This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…
Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…
Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…
Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on…