MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views

• URL: http://arxiv.org/abs/2411.04924v1
• Date: Thu, 07 Nov 2024 17:59:31 GMT
• Title: MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
• Authors: Yuedong Chen, Chuanxia Zheng, Haofei Xu, Bohan Zhuang, Andrea Vedaldi, Tat-Jen Cham, Jianfei Cai,
• Abstract summary: We introduce MVSplat360, a feed-forward approach for 360deg novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficient visual information provided. Our model is end-to-end trainable and supports rendering arbitrary views with as few as 5 sparse input views.
• Score: 90.26609689682876
• License:
• Abstract: We introduce MVSplat360, a feed-forward approach for 360{\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficient visual information provided, making it challenging for conventional methods to achieve high-quality results. Our MVSplat360 addresses this by effectively combining geometry-aware 3D reconstruction with temporally consistent video generation. Specifically, it refactors a feed-forward 3D Gaussian Splatting (3DGS) model to render features directly into the latent space of a pre-trained Stable Video Diffusion (SVD) model, where these features then act as pose and visual cues to guide the denoising process and produce photorealistic 3D-consistent views. Our model is end-to-end trainable and supports rendering arbitrary views with as few as 5 sparse input views. To evaluate MVSplat360's performance, we introduce a new benchmark using the challenging DL3DV-10K dataset, where MVSplat360 achieves superior visual quality compared to state-of-the-art methods on wide-sweeping or even 360{\deg} NVS tasks. Experiments on the existing benchmark RealEstate10K also confirm the effectiveness of our model. The video results are available on our project page: https://donydchen.github.io/mvsplat360.

Related papers

• SplatFormer: Point Transformer for Robust 3D Gaussian Splatting [18.911307036504827]
  3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. rendering quality significantly deteriorates when test views deviate from the camera angles used during training, posing a major challenge for applications in immersive free-viewpoint rendering and navigation. We introduce SplatFormer, the first point transformer model specifically designed to operate on Gaussian splats. Our model significantly improves rendering quality under extreme novel views, achieving state-of-the-art performance in these challenging scenarios and outperforming various 3DGS regularization techniques, multi-scene models tailored for sparse view synthesis, and diffusion
  arXiv  Detail & Related papers  (2024-11-10T08:23:27Z)
• Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priors [51.36238367193988]
  We tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM) We present SparseSplat360, a method that employs a cascade of in-painting and artifact removal models to fill in missing details and clean novel views. Our method generates entire 360 scenes from as few as 9 input views, with a high degree of foreground and background detail.
  arXiv  Detail & Related papers  (2024-05-26T11:01:39Z)
• See360: Novel Panoramic View Interpolation [24.965259708297932]
  See360 is a versatile and efficient framework for 360 panoramic view using latent space viewpoint estimation. We show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for four datasets.
  arXiv  Detail & Related papers  (2024-01-07T09:17:32Z)
• NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes [59.15910989235392]
  We introduce NeO 360, Neural fields for sparse view synthesis of outdoor scenes. NeO 360 is a generalizable method that reconstructs 360deg scenes from a single or a few posed RGB images. Our representation combines the best of both voxel-based and bird's-eye-view (BEV) representations.
  arXiv  Detail & Related papers  (2023-08-24T17:59:50Z)
• S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces [75.30792581941789]
  Neural rendering of implicit surfaces performs well in 3D vision applications. When only sparse input images are available, output quality drops significantly due to the shape-radiance ambiguity problem. We propose to regularize neural rendering optimization with an MVS solution.
  arXiv  Detail & Related papers  (2023-03-30T21:10:58Z)
• Multi-View Transformer for 3D Visual Grounding [64.30493173825234]
  We propose a Multi-View Transformer (MVT) for 3D visual grounding. We project the 3D scene to a multi-view space, in which the position information of the 3D scene under different views are modeled simultaneously and aggregated together.
  arXiv  Detail & Related papers  (2022-04-05T12:59:43Z)
• SHD360: A Benchmark Dataset for Salient Human Detection in 360{\deg} Videos [26.263614207849276]
  We propose SHD360, the first 360deg video SHD dataset collecting various real-life daily scenes. SHD360 contains 16,238 salient human instances with manually annotated pixel-wise ground truth. Our proposed dataset and benchmark could serve as a good starting point for advancing human-centric researches towards 360deg panoramic data.
  arXiv  Detail & Related papers  (2021-05-24T23:51:29Z)
• ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos [5.831115928056554]
  This paper proposes ATSal, a novel attention based (head-eye) saliency model for 360degree videos. We compare the proposed approach to other state-of-the-art saliency models on two datasets: Salient360! and VR-EyeTracking. Experimental results on over 80 ODV videos (75K+ frames) show that the proposed method outperforms the existing state-of-the-art.
  arXiv  Detail & Related papers  (2020-11-20T19:19:48Z)
• Stable View Synthesis [100.86844680362196]
  We present Stable View Synthesis (SVS) Given a set of source images depicting a scene from freely distributed viewpoints, SVS synthesizes new views of the scene. SVS outperforms state-of-the-art view synthesis methods both quantitatively and qualitatively on three diverse real-world datasets.
  arXiv  Detail & Related papers  (2020-11-14T07:24:43Z)

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.