Related papers: ShapeFusion: A 3D diffusion model for localized sh…

This paper proposes Instruct 4D-to-4D that achieves 4D awareness and spatial-temporal consistency for 2D diffusion models to generate high-quality instruction-guided dynamic scene editing results. Traditional applications of 2D diffusion…

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…

Recently, several works tackled the video editing task fostered by the success of large-scale text-to-image generative models. However, most of these methods holistically edit the frame using the text, exploiting the prior given by…

Patient data from real-world clinical practice often suffers from data scarcity and long-tail imbalances, leading to biased outcomes or algorithmic unfairness. This study addresses these challenges by generating lesion-containing…

We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent…

Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview…

Pre-trained conditional diffusion models have demonstrated remarkable potential in image editing. However, they often face challenges with temporal consistency, particularly in the talking head domain, where continuous changes in facial…

We propose a diffusion-based approach for Text-to-Image (T2I) generation with consistent and interactive 3D layout control and editing. While prior methods improve spatial adherence using 2D cues or iterative copy-warp-paste strategies,…

Large-scale pre-trained vision-language models allow for the zero-shot text-based generation of 3D avatars. The previous state-of-the-art method utilized CLIP to supervise neural implicit models that reconstructed a human body mesh.…

Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process…

High-quality reconstruction of controllable 3D head avatars from 2D videos is highly desirable for virtual human applications in movies, games, and telepresence. Neural implicit fields provide a powerful representation to model 3D head…

Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference image in the generation. Although effective,…

Triangulated meshes have become ubiquitous discrete-surface representations. In this paper we address the problem of how to maintain the manifold properties of a surface while it undergoes strong deformations that may cause topological…

Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, very few works have done so for video editing. We present the…

We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds). Our method distills diffusion features from image foundational models onto input shapes.…

Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…

Diffusion models have enabled high-quality, conditional image editing capabilities. We propose to expand their arsenal, and demonstrate that off-the-shelf diffusion models can be used for a wide range of cross-domain compositing tasks.…

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from…