Related papers: Synthesizing Consistent Novel Views via 3D Epipola…
Novel view synthesis (NVS) is a cornerstone for image-to-3d creation. However, existing works still struggle to maintain consistency between the generated views and the input views, especially when there is a significant camera pose…
Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful,…
Scenes reconstructed by 3D Gaussian Splatting (3DGS) trained on low-resolution (LR) images are unsuitable for high-resolution (HR) rendering. Consequently, a 3DGS super-resolution (SR) method is needed to bridge LR inputs and HR rendering.…
In this work we introduce a new self-supervised, semi-parametric approach for synthesizing novel views of a vehicle starting from a single monocular image. Differently from parametric (i.e. entirely learning-based) methods, we show how…
Deep convolutional neural network (DCNN) has been successfully applied to depth map super-resolution and outperforms existing methods by a wide margin. However, there still exist two major issues with these DCNN based depth map…
We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training…
We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffusion model by extending its self-attention layers with…
Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and…
Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…
Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…
Large image diffusion models have demonstrated zero-shot capability in novel view synthesis (NVS). However, existing diffusion-based NVS methods struggle to generate novel views that are accurately consistent with the corresponding ground…
Satellite-to-street view synthesis aims at generating a realistic street-view image from its corresponding satellite-view image. Although stable diffusion models have exhibit remarkable performance in a variety of image generation…
Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or…
The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and semantic maps by reconstructing generalizable Neural Radiance…
World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user…
Repurposing pre-trained diffusion models has been proven to be effective for NVS. However, these methods are mostly limited to a single object; directly applying such methods to compositional multi-object scenarios yields inferior results,…
The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…
Despite recent advances in appearance-based gaze estimation techniques, the need for training data that covers the target head pose and gaze distribution remains a crucial challenge for practical deployment. This work examines a novel…
A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to single-view view…
Novel view synthesis refers to the problem of synthesizing novel viewpoints of a scene given the images from a few viewpoints. This is a fundamental problem in computer vision and graphics, and enables a vast variety of applications such as…