Related papers: A Novel Image-centric Approach Towards Direct Volu…
Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation…
We introduce the Virtual Fitting Room (VFR), a novel video generative model that produces arbitrarily long virtual try-on videos. Our VFR models long video generation tasks as an auto-regressive, segment-by-segment generation process,…
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications. But the practice is severely limited by high computational costs in the rendering process. To…
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…
Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D…
Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled at the element level, enabling intuitive modifications such as adjusting shapes, altering…
Recent advancements in neural networks, supported by foundational theoretical insights, emphasize the superior representational power of complex numbers. However, their adoption in randomized neural networks (RNNs) has been limited due to…
In this paper, we address the problem of enhancing perceptual quality in video super-resolution (VSR) using Diffusion Models (DMs) while ensuring temporal consistency among frames. We present StableVSR, a VSR method based on DMs that can…
Besides suppressing all undesired sound sources, an important objective of a binaural noise reduction algorithm for hearing devices is the preservation of the binaural cues, aiming at preserving the spatial perception of the acoustic scene.…
The methods of extracting image features are the key to many image processing tasks. At present, the most popular method is the deep neural network which can automatically extract robust features through end-to-end training instead of…
Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…
We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to…
High Dynamic Range (HDR) imaging aims to generate an artifact-free HDR image with realistic details by fusing multi-exposure Low Dynamic Range (LDR) images. Caused by large motion and severe under-/over-exposure among input LDR images, HDR…
The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such as vector graphics. Unfortunately due to their variable…
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth…
Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…
Face Recognition (FR) technology has made significant strides with the emergence of deep learning. Typically, most existing FR models are built upon Convolutional Neural Networks (CNN) and take RGB face images as the model's input. In this…
This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques…
Generating diverse and high-quality 3D assets automatically poses a fundamental yet challenging task in 3D computer vision. Despite extensive efforts in 3D generation, existing optimization-based approaches struggle to produce large-scale…
We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and…