ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis

• URL: http://arxiv.org/abs/2402.02906v2
• Date: Wed, 04 Jun 2025 19:52:23 GMT
• Title: ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
• Authors: Bernard Spiegl, Andrea Perin, Stéphane Deny, Alexander Ilin,
• Abstract summary: ViewFusion is an end-to-end generative approach to novel view synthesis with unparalleled flexibility.<n>Our method is tested on the relatively small Neural 3D Mesh Renderer dataset.
• Score: 47.0052408875896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning is providing a wealth of new approaches to the problem of novel view synthesis, from Neural Radiance Field (NeRF) based approaches to end-to-end style architectures. Each approach offers specific strengths but also comes with limitations in their applicability. This work introduces ViewFusion, an end-to-end generative approach to novel view synthesis with unparalleled flexibility. ViewFusion consists in simultaneously applying a diffusion denoising step to any number of input views of a scene, then combining the noise gradients obtained for each view with an (inferred) pixel-weighting mask, ensuring that for each region of the target view only the most informative input views are taken into account. Our approach resolves several limitations of previous approaches by (1) being trainable and generalizing across multiple scenes and object classes, (2) adaptively taking in a variable number of pose-free views at both train and test time, (3) generating plausible views even in severely underdetermined conditions (thanks to its generative nature) -- all while generating views of quality on par or even better than comparable methods. Limitations include not generating a 3D embedding of the scene, resulting in a relatively slow inference speed, and our method only being tested on the relatively small Neural 3D Mesh Renderer dataset. Code is available at https://github.com/bronemos/view-fusion.

Related papers

• AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction [69.65671384868344]
  We propose AR-1-to-3, a novel next-view prediction paradigm based on diffusion models.<n>We show that our method significantly improves the consistency between the generated views and the input views, producing high-fidelity 3D assets.
  arXiv  Detail & Related papers  (2025-03-17T08:39:10Z)
• Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training [102.82553402539139]
  Large diffusion models demonstrate remarkable zero-shot capabilities in novel view synthesis from a single image. These models often face challenges in maintaining consistency across novel and reference views. We propose to use epipolar geometry to locate and retrieve overlapping information from the input view. This information is then incorporated into the generation of target views, eliminating the need for training or fine-tuning.
  arXiv  Detail & Related papers  (2025-02-25T14:04:22Z)
• MultiDiff: Consistent Novel View Synthesis from a Single Image [60.04215655745264]
  MultiDiff is a novel approach for consistent novel view synthesis of scenes from a single RGB image. Our results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet.
  arXiv  Detail & Related papers  (2024-06-26T17:53:51Z)
• ViewFusion: Towards Multi-View Consistency via Interpolated Denoising [48.02829400913904]
  We introduce ViewFusion, a training-free algorithm that can be seamlessly integrated into existing pre-trained diffusion models. Our approach adopts an auto-regressive method that implicitly leverages previously generated views as context for the next view generation. Our framework successfully extends single-view conditioned models to work in multiple-view conditional settings without any additional fine-tuning.
  arXiv  Detail & Related papers  (2024-02-29T04:21:38Z)
• VaLID: Variable-Length Input Diffusion for Novel View Synthesis [36.57742242154048]
  Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their corresponding poses, is a fundamental problem in 3D Vision. We try to process each pose image pair separately and then fuse them as a unified visual representation which will be injected into the model. The Multi-view Cross Former module is proposed which maps variable-length input data to fix-size output data.
  arXiv  Detail & Related papers  (2023-12-14T12:52:53Z)
• UpFusion: Novel View Diffusion from Unposed Sparse View Observations [66.36092764694502]
  UpFusion can perform novel view synthesis and infer 3D representations for an object given a sparse set of reference images. We show that this mechanism allows generating high-fidelity novel views while improving the synthesis quality given additional (unposed) images.
  arXiv  Detail & Related papers  (2023-12-11T18:59:55Z)
• Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models [16.326276673056334]
  Consistent-1-to-3 is a generative framework that significantly mitigates this issue. We decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information.
  arXiv  Detail & Related papers  (2023-10-04T17:58:57Z)
• Multi-Plane Neural Radiance Fields for Novel View Synthesis [5.478764356647437]
  Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints. In this work, we examine the performance, generalization, and efficiency of single-view multi-plane neural radiance fields. We propose a new multiplane NeRF architecture that accepts multiple views to improve the synthesis results and expand the viewing range.
  arXiv  Detail & Related papers  (2023-03-03T06:32:55Z)
• Novel View Synthesis with Diffusion Models [56.55571338854636]
  We present 3DiM, a diffusion model for 3D novel view synthesis. It is able to translate a single input view into consistent and sharp completions across many views. 3DiM can generate multiple views that are 3D consistent using a novel technique called conditioning.
  arXiv  Detail & Related papers  (2022-10-06T16:59:56Z)
• Vision Transformer for NeRF-Based View Synthesis from a Single Input Image [49.956005709863355]
  We propose to leverage both the global and local features to form an expressive 3D representation. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model.
  arXiv  Detail & Related papers  (2022-07-12T17:52:04Z)
• IBRNet: Learning Multi-View Image-Based Rendering [67.15887251196894]
  We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering.
  arXiv  Detail & Related papers  (2021-02-25T18:56:21Z)

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.