Related papers: PipeFlow: Pipelined Processing and Motion-Aware Fr…
Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space…
Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i.e., diffusion extrapolation, significantly improves diffusion adaptability. We propose tuning-free CutDiffusion, aimed at simplifying…
High-fidelity, high-resolution numerical simulations are crucial for studying complex multiscale phenomena in fluid dynamics, such as turbulent flows and ocean waves. However, direct numerical simulations with high-resolution solvers are…
Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through…
Video frame interpolation aims to synthesize one or multiple frames between two consecutive frames in a video. It has a wide range of applications including slow-motion video generation, frame-rate up-scaling and developing video codecs.…
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…
Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction,…
Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image…
Deep neural networks with large model sizes achieve state-of-the-art results for tasks in computer vision (CV) and natural language processing (NLP). However, these large-scale models are too compute- or memory-intensive for…
In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…
We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze…
3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generative paradigms, 3D AI generation remains dominated by training-free editing pipelines. A…
Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the regions to be edited and faithfully perform precise edits.…
Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…
Image fusion is a fundamental and important task in computer vision, aiming to combine complementary information from different modalities to fuse images. In recent years, diffusion models have made significant developments in the field of…
Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should maintain the temporal consistency of the filled area. In this…
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…
Recent inversion-free, flow-based image editing methods such as FlowEdit leverages a pre-trained noise-to-image flow model such as Stable Diffusion 3, enabling text-driven manipulation by solving an ordinary differential equation (ODE).…
Diffusion models have achieved remarkable success in video generation; however, the high computational cost of the denoising process remains a major bottleneck. Existing approaches have shown promise in reducing the number of diffusion…
We present a novel simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on a pre-trained optical flow model or a U-Net based pyramid network for motion…