Related papers: DragLoRA: Online Optimization of LoRA Adapters for…
Existing diffusion-based methods have achieved impressive results in human motion editing. However, these methods often exhibit significant ghosting and body distortion in unseen in-the-wild cases. In this paper, we introduce…
In this paper, we introduce GoodDrag, a novel approach to improve the stability and image quality of drag editing. Unlike existing methods that struggle with accumulated perturbations and often result in distortions, GoodDrag introduces an…
Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in…
Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…
Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges:…
Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions auto-regressively in a fixed left-to-right order or attach…
Video editing is a challenging task that requires manipulating videos on both the spatial and temporal dimensions. Existing methods for video editing mainly focus on changing the appearance or style of the objects in the video, while…
Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…
Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…
Direct mesh editing and deformation are key components in the geometric modeling and animation pipeline. Mesh editing methods are typically framed as optimization problems combining user-specified vertex constraints with a regularizer that…
Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…
Recent advances in diffusion models have significantly improved the synthesis of materials, textures, and 3D shapes. By conditioning these models via text or images, users can guide the generation, reducing the time required to create…
Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…
Image manipulation under the guidance of textual descriptions has recently received a broad range of attention. In this study, we focus on the regional editing of images with the guidance of given text prompts. Different from current…
Recent advances in large-scale text-to-image diffusion models have heightened concerns about their potential misuse, especially in generating harmful or misleading content. This underscores the urgent need for effective machine unlearning,…
Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…
Current controllable diffusion models typically rely on fixed architectures that modify intermediate activations to inject guidance conditioned on a new modality. This approach uses a static conditioning strategy for a dynamic, multi-stage…
Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method that leverages low-rank adaptation of weight matrices, has emerged as a prevalent technique for fine-tuning pre-trained models such as large language models and diffusion…
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…