Related papers: GeoDiffMM: Geometry-Guided Conditional Diffusion f…
Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental…
Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…
This paper introduces a novel speech enhancement (SE) approach based on a denoising diffusion probabilistic model (DDPM), termed Guided diffusion for speech enhancement (GDiffuSE). In contrast to conventional methods that directly map noisy…
Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured…
Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…
Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output,…
Underwater vision is crucial for autonomous underwater vehicles (AUVs), and enhancing degraded underwater images in real-time on a resource-constrained AUV is a key challenge due to factors like light absorption and scattering, or the…
We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray…
Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a…
We introduce GeMS, a framework for 3D Gaussian Splatting (3DGS) designed to handle severely motion-blurred images. State-of-the-art deblurring methods for extreme blur, such as ExBluRF, as well as Gaussian Splatting-based approaches like…
Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Although the Denoising…
Neural rendering for interactive applications requires translating geometric and material properties (G-buffer) to photorealistic images with realistic lighting on a frame-by-frame basis. While recent diffusion-based approaches show promise…
Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications…
Recent video diffusion models have demonstrated their great capability in generating visually-pleasing results, while synthesizing the correct physical effects in generated videos remains challenging. The complexity of real-world motions,…
The ability to amplify or reduce subtle image changes over time is useful in contexts such as video editing, medical video analysis, product quality control and sports. In these contexts there is often large motion present which severely…
Diffusion models have garnered considerable interest in computer vision, owing both to their capacity to synthesize photorealistic images and to their proven effectiveness in image reconstruction tasks. However, existing approaches fail to…
Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to…
Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents, is a critical capability. While current approaches handle…
Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised training, which restricts their adaptation to complex real…