Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model

• URL: http://arxiv.org/abs/2504.02764v1
• Date: Thu, 03 Apr 2025 17:00:44 GMT
• Title: Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model
• Authors: Shengjun Zhang, Jinzhao Li, Xin Fei, Hao Liu, Yueqi Duan,
• Abstract summary: Scene Splatter is a momentum-based paradigm for video diffusion to generate generic scenes from single image.<n>We construct noisy samples from original features as momentum to enhance video details and maintain scene consistency.<n>Our cascaded momentum enables video diffusion models to generate both high-fidelity and consistent novel views.
• Score: 14.775908473190684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose Scene Splatter, a momentum-based paradigm for video diffusion to generate generic scenes from single image. Existing methods, which employ video generation models to synthesize novel views, suffer from limited video length and scene inconsistency, leading to artifacts and distortions during further reconstruction. To address this issue, we construct noisy samples from original features as momentum to enhance video details and maintain scene consistency. However, for latent features with the perception field that spans both known and unknown regions, such latent-level momentum restricts the generative ability of video diffusion in unknown regions. Therefore, we further introduce the aforementioned consistent video as a pixel-level momentum to a directly generated video without momentum for better recovery of unseen regions. Our cascaded momentum enables video diffusion models to generate both high-fidelity and consistent novel views. We further finetune the global Gaussian representations with enhanced frames and render new frames for momentum update in the next step. In this manner, we can iteratively recover a 3D scene, avoiding the limitation of video length. Extensive experiments demonstrate the generalization capability and superior performance of our method in high-fidelity and consistent scene generation.

Related papers

• Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
  We introduce a large-scale reconstruction model that uses latents from a video diffusion model to predict 3D Gaussian Splattings for the scenes.<n>We train the 3D reconstruction model to operate on the video latent space with a progressive training strategy, enabling the efficient generation of high-quality, wide-scope, and generic 3D scenes.
  arXiv  Detail & Related papers  (2024-12-16T18:58:17Z)
• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis [63.169364481672915]
  We propose textbfViewCrafter, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames.
  arXiv  Detail & Related papers  (2024-09-03T16:53:19Z)
• Anchored Diffusion for Video Face Reenactment [17.343307538702238]
  We introduce Anchored Diffusion, a novel method for synthesizing relatively long and seamless videos. We train our model on video sequences with random non-uniform temporal spacing and incorporate temporal information via external guidance. During inference, we leverage the transformer architecture to modify the diffusion process, generating a batch of non-uniform sequences anchored to a common frame.
  arXiv  Detail & Related papers  (2024-07-21T13:14:17Z)
• SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix [60.48666051245761]
  We propose a pose-free and training-free approach for generating 3D stereoscopic videos. Our method warps a generated monocular video into camera views on stereoscopic baseline using estimated video depth. We develop a disocclusion boundary re-injection scheme that further improves the quality of video inpainting.
  arXiv  Detail & Related papers  (2024-06-29T08:33:55Z)
• GenDeF: Learning Generative Deformation Field for Video Generation [89.49567113452396]
  We propose to render a video by warping one static image with a generative deformation field (GenDeF) Such a pipeline enjoys three appealing advantages.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• Fast View Synthesis of Casual Videos with Soup-of-Planes [24.35962788109883]
  Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. Our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.
  arXiv  Detail & Related papers  (2023-12-04T18:55:48Z)
• VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models [58.93124686141781]
  Video Motion Customization (VMC) is a novel one-shot tuning approach crafted to adapt temporal attention layers within video diffusion models. Our approach introduces a novel motion distillation objective using residual vectors between consecutive frames as a motion reference. We validate our method against state-of-the-art video generative models across diverse real-world motions and contexts.
  arXiv  Detail & Related papers  (2023-12-01T06:50:11Z)
• Latent Video Diffusion Models for High-Fidelity Long Video Generation [58.346702410885236]
  We introduce lightweight video diffusion models using a low-dimensional 3D latent space. We also propose hierarchical diffusion in the latent space such that longer videos with more than one thousand frames can be produced. Our framework generates more realistic and longer videos than previous strong baselines.
  arXiv  Detail & Related papers  (2022-11-23T18:58:39Z)
• Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video [76.19076002661157]
  Non-Rigid Neural Radiance Fields (NR-NeRF) is a reconstruction and novel view synthesis approach for general non-rigid dynamic scenes. We show that even a single consumer-grade camera is sufficient to synthesize sophisticated renderings of a dynamic scene from novel virtual camera views.
  arXiv  Detail & Related papers  (2020-12-22T18:46:12Z)

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.