StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart

• URL: http://arxiv.org/abs/2411.14295v1
• Date: Thu, 21 Nov 2024 16:41:55 GMT
• Title: StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart
• Authors: Jian Shi, Qian Wang, Zhenyu Li, Peter Wonka,
• Abstract summary: We introduce textitStereoCrafter-Zero, a novel framework for zero-shot stereo video generation. Key innovations include a noisy restart strategy to initialize stereo-aware latents and an iterative refinement process. Our framework is robust and adaptable across various diffusion models, setting a new benchmark for zero-shot stereo video generation.
• Score: 45.27524689977587
• License:
• Abstract: Generating high-quality stereo videos that mimic human binocular vision requires maintaining consistent depth perception and temporal coherence across frames. While diffusion models have advanced image and video synthesis, generating high-quality stereo videos remains challenging due to the difficulty of maintaining consistent temporal and spatial coherence between left and right views. We introduce \textit{StereoCrafter-Zero}, a novel framework for zero-shot stereo video generation that leverages video diffusion priors without the need for paired training data. Key innovations include a noisy restart strategy to initialize stereo-aware latents and an iterative refinement process that progressively harmonizes the latent space, addressing issues like temporal flickering and view inconsistencies. Comprehensive evaluations, including quantitative metrics and user studies, demonstrate that \textit{StereoCrafter-Zero} produces high-quality stereo videos with improved depth consistency and temporal smoothness, even when depth estimations are imperfect. Our framework is robust and adaptable across various diffusion models, setting a new benchmark for zero-shot stereo video generation and enabling more immersive visual experiences. Our code can be found in~\url{https://github.com/shijianjian/StereoCrafter-Zero}.

Related papers

• ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning [43.105154507379076]
  textitImmersePro is a framework specifically designed to transform single-view videos into stereo videos. textitImmersePro employs implicit disparity guidance, enabling the generation of stereo pairs from video sequences without the need for explicit disparity maps. Our experiments demonstrate the effectiveness of textitImmersePro in producing high-quality stereo videos, offering significant improvements over existing methods.
  arXiv  Detail & Related papers  (2024-09-30T22:19:32Z)
• Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality [65.70936336240554]
  Real-time Stereo Matching is a cornerstone algorithm for many Extended Reality (XR) applications, such as indoor 3D understanding, video pass-through, and mixed-reality games. One of the major difficulties is the lack of high-quality indoor video stereo training datasets captured by head-mounted VR/AR glasses. We introduce a novel video stereo synthetic dataset that comprises renderings of various indoor scenes and realistic camera motion captured by a 6-DoF moving VR/AR head-mounted display (HMD). This facilitates the evaluation of existing approaches and promotes further research on indoor augmented reality scenarios.
  arXiv  Detail & Related papers  (2023-09-08T07:53:58Z)
• DynamicStereo: Consistent Dynamic Depth from Stereo Videos [91.1804971397608]
  We propose DynamicStereo to estimate disparity for stereo videos. The network learns to pool information from neighboring frames to improve the temporal consistency of its predictions. We also introduce Dynamic Replica, a new benchmark dataset containing synthetic videos of people and animals in scanned environments.
  arXiv  Detail & Related papers  (2023-05-03T17:40:49Z)
• Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators [70.17041424896507]
  Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. We propose a new task of zero-shot text-to-video generation using existing text-to-image synthesis methods. Our method performs comparably or sometimes better than recent approaches, despite not being trained on additional video data.
  arXiv  Detail & Related papers  (2023-03-23T17:01:59Z)
• Towards Smooth Video Composition [59.134911550142455]
  Video generation requires consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs) We show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality.
  arXiv  Detail & Related papers  (2022-12-14T18:54:13Z)
• Strumming to the Beat: Audio-Conditioned Contrastive Video Textures [112.6140796961121]
  We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures, which showed that plausible new videos could be generated from a single one by stitching its frames together in a novel yet consistent order. Our model outperforms baselines on human perceptual scores, can handle a diverse range of input videos, and can combine semantic and audio-visual cues in order to synthesize videos that synchronize well with an audio signal.
  arXiv  Detail & Related papers  (2021-04-06T17:24:57Z)
• Sound2Sight: Generating Visual Dynamics from Sound and Context [36.38300120482868]
  We present Sound2Sight, a deep variational framework, that is trained to learn a per frame prior conditioned on a joint embedding of audio and past frames. To improve the quality and coherence of the generated frames, we propose a multimodal discriminator. Our experiments demonstrate that Sound2Sight significantly outperforms the state of the art in the generated video quality.
  arXiv  Detail & Related papers  (2020-07-23T16:57:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.