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

TL;DR

GenWarp introduces a semantic-preserving generative warping framework that enhances single-image novel view synthesis by combining geometric warping with T2I models, outperforming existing methods in diverse scenarios.

Contribution

The paper proposes a novel generative warping approach that preserves semantics and improves view synthesis from a single image by integrating cross-view and self-attention mechanisms.

Findings

Outperforms existing methods in in-domain scenarios

Effective in out-of-domain scenarios

Addresses noise and semantic loss issues in warping

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/.