相关论文: MiVID: Multi-Strategic Self-Supervision for Video …
Object tracking is a fundamental task in computer vision, requiring the localization of objects of interest across video frames. Diffusion models have shown remarkable capabilities in visual generation, making them well-suited for…
Recent advancements in diffusion frameworks have significantly enhanced video editing, achieving high fidelity and strong alignment with textual prompts. However, conventional approaches using image diffusion models fall short in handling…
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…
Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no explicit temporal modeling. This paper demonstrates that these…
Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…
Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised…
Visible and infrared image fusion (VIF) has gained significant attention in recent years due to its wide application in tasks such as scene segmentation and object detection. VIF methods can be broadly classified into traditional VIF…
Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…
Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video…
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,…
We present 4DiM, a cascaded diffusion model for 4D novel view synthesis (NVS), supporting generation with arbitrary camera trajectories and timestamps, in natural scenes, conditioned on one or more images. With a novel architecture and…
In this paper, we propose a variance-preserving interpolation framework to improve diffusion models for single-channel speech enhancement (SE) and automatic speech recognition (ASR). This new variance-preserving interpolation diffusion…
Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. We introduce DiViD,…
The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information. However, such a setup commonly…
Diffusion-based image editing models have made remarkable progress in recent years. However, achieving high-quality video editing remains a significant challenge. One major hurdle is the absence of open-source, large-scale video editing…
With the development of video generation models has advanced significantly in recent years, we adopt large-scale image-to-video diffusion models for video frame interpolation. We present a conditional encoder designed to adapt an…
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…
Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural…
Facial video editing has become increasingly important for content creators, enabling the manipulation of facial expressions and attributes. However, existing models encounter challenges such as poor editing quality, high computational…