相关论文: Novel View Synthesis as Video Completion

Neural Radiance Field (NeRF) has broken new ground in the novel view synthesis due to its simple concept and state-of-the-art quality. However, it suffers from severe performance degradation unless trained with a dense set of images with…

Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This…

Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and…

This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual…

Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple diffusion steps.…

We explore novel-view synthesis for dynamic scenes from monocular videos. Prior approaches rely on costly test-time optimization of 4D representations or do not preserve scene geometry when trained in a feed-forward manner. Our approach is…

Virtual reality (VR) headsets provide an immersive, stereoscopic visual experience, but at the cost of blocking users from directly observing their physical environment. Passthrough techniques are intended to address this limitation by…

Although neural radiance fields (NeRF) have shown impressive advances for novel view synthesis, most methods typically require multiple input images of the same scene with accurate camera poses. In this work, we seek to substantially reduce…

We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, leading to…

Visual anagrams are images that change appearance upon transformation, like flipping or rotation. With the advent of diffusion models, generating such optical illusions can be achieved by averaging noise across multiple views during the…

Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards…

We introduce a principled approach for synthesizing new views of a scene given a single source image. Previous methods for novel view synthesis can be divided into image-based rendering methods (e.g. flow prediction) or pixel generation…

This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety of dynamic scenes, complete with detailed textures,…

In order to be able to deliver today's voluminous amount of video contents through limited bandwidth channels in a perceptually optimal way, it is important to consider perceptual trade-offs of compression and space-time downsampling…

Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but…

In this work, we address dynamic view synthesis from monocular videos as an inverse problem in a training-free setting. By redesigning the noise initialization phase of a pre-trained video diffusion model, we enable high-fidelity dynamic…

Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampling, resulting in…

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,…

Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising…

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured…