SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations

• URL: http://arxiv.org/abs/2505.11992v1
• Date: Sat, 17 May 2025 13:05:13 GMT
• Title: SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
• Authors: Songchun Zhang, Huiyao Xu, Sitong Guo, Zhongwei Xie, Pengwei Liu, Hujun Bao, Weiwei Xu, Changqing Zou,
• Abstract summary: This work takes on the challenge of reconstructing 3D scenes from sparse or single-view inputs.<n>We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations.<n>Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency.
• Score: 42.69229582451846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-view inputs. We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations, thereby alleviating reconstruction ambiguity. Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency, further reinforced by a unified scale estimation strategy to handle scale discrepancies across datasets. Furthermore, by integrating monocular depth priors with semantic features in the video latent space, our framework directly regresses 3D Gaussian primitives and efficiently processes long-sequence features using a hybrid network structure. Extensive experiments show our method enhances sparse view reconstruction and restores the realistic appearance of 3D scenes.

Related papers

• DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos [52.46386528202226]
  We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM)<n>It is the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene.<n>It achieves performance on par with state-of-the-art monocular video 3D tracking methods.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• ACT-R: Adaptive Camera Trajectories for 3D Reconstruction from Single Image [12.942796503696194]
  We introduce adaptive view planning to multi-view synthesis.<n>We generate a sequence of views, leveraging temporal consistency to enhance 3D coherence.<n>Our method significantly improves 3D reconstruction over SOTA on the unseen GSO dataset.
  arXiv  Detail & Related papers  (2025-05-13T05:31:59Z)
• 3D Scene Understanding Through Local Random Access Sequence Modeling [12.689247678229382]
  3D scene understanding from single images is a pivotal problem in computer vision.<n>We propose an autoregressive generative approach called Local Random Access Sequence (LRAS) modeling.<n>By utilizing optical flow as an intermediate representation for 3D scene editing, our experiments demonstrate that LRAS achieves state-of-the-art novel view synthesis and 3D object manipulation capabilities.
  arXiv  Detail & Related papers  (2025-04-04T18:59:41Z)
• ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image [4.366356163044466]
  Existing methods are often limited to reconstruct low-consistency 3D scenes with narrow fields of view from single-view input.<n>We propose ExScene, a two-stage pipeline to reconstruct an immersive 3D scene from any given single-view image.<n>ExScene achieves consistent and immersive scene reconstruction using only single-view input.
  arXiv  Detail & Related papers  (2025-03-31T09:33:22Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment [63.21396416244634]
  VideoLifter is a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis.<n>It significantly accelerates the reconstruction process, reducing training time by over 82% while holding better visual quality than current SOTA methods.
  arXiv  Detail & Related papers  (2025-01-03T18:52:36Z)
• Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
  We introduce a large-scale reconstruction model that leverages latents from a video diffusion model to predict 3D Gaussian Splattings of scenes in a feed-forward manner.<n>We train the 3D reconstruction model to operate on the video latent space with a progressive learning 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)
• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features [65.8738034806085]
  DistillNeRF is a self-supervised learning framework for understanding 3D environments in autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs.
  arXiv  Detail & Related papers  (2024-06-17T21:15:13Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)

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.