GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

• URL: http://arxiv.org/abs/2405.17251v2
• Date: Thu, 26 Sep 2024 08:22:52 GMT
• Title: GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
• Authors: Junyoung Seo, Kazumi Fukuda, Takashi Shibuya, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim, Yuki Mitsufuji,
• Abstract summary: We propose a semantic-preserving generative warping framework to generate novel views from a single image. Our approach addresses the limitations of existing methods by conditioning the generative model on source view images. Our model outperforms existing methods in both in-domain and out-of-domain scenarios.
• Score: 47.38125925469167
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image (T2I) models with monocular depth estimation (MDE) has shown promise in handling in-the-wild images. In these methods, an input view is geometrically warped to novel views with estimated depth maps, then the warped image is inpainted by T2I models. However, they struggle with noisy depth maps and loss of semantic details when warping an input view to novel viewpoints. In this paper, we propose a novel approach for single-shot novel view synthesis, a semantic-preserving generative warping framework that enables T2I generative models to learn where to warp and where to generate, through augmenting cross-view attention with self-attention. Our approach addresses the limitations of existing methods by conditioning the generative model on source view images and incorporating geometric warping signals. Qualitative and quantitative evaluations demonstrate that our model outperforms existing methods in both in-domain and out-of-domain scenarios. Project page is available at https://GenWarp-NVS.github.io/.

Related papers

• 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)
• DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views [20.685453627120832]
  Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings. DreamSparse is capable of synthesizing high-quality novel views for both object and scene-level images.
  arXiv  Detail & Related papers  (2023-06-06T05:26:26Z)
• BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing [73.74570290836152]
  BLIP-Diffusion is a new subject-driven image generation model that supports multimodal control. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation.
  arXiv  Detail & Related papers  (2023-05-24T04:51:04Z)
• 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)
• Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing [71.19528222206088]
  We propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. Our method achieves the new state-of-the-art performance on the Helen, CelebA-HQ, and LapaMask datasets.
  arXiv  Detail & Related papers  (2022-03-28T02:12:30Z)
• ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers [34.4824364161812]
  Novel view synthesis is a problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene, which requires learning priors. We propose a 2D-only method that maps multiple context views and a query pose to a new image in a single pass of a neural network.
  arXiv  Detail & Related papers  (2022-03-18T21:08:23Z)
• Deep View Synthesis via Self-Consistent Generative Network [41.34461086700849]
  View synthesis aims to produce unseen views from a set of views captured by two or more cameras at different positions. To address this issue, most existing methods seek to exploit the geometric information to match pixels. We propose a novel deep generative model, called Self-Consistent Generative Network (SCGN), which synthesizes novel views without explicitly exploiting the geometric information.
  arXiv  Detail & Related papers  (2021-01-19T10:56:00Z)

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.