Related papers: Explicit Correspondence Matching for Generalizable…
In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera images. Since recent stereo matching has demonstrated accurate geometry prediction, we introduce stereo matching…
Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused on developing data-driven discriminative models for scene…
We present a novel feature matching algorithm that systematically utilizes the geometric properties of features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes with the…
We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in…
Implicit representations like Neural Radiance Fields (NeRF) showed impressive results for photorealistic rendering of complex scenes with fine details. However, ideal or near-perfectly specular reflecting objects such as mirrors, which are…
Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning…
Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static…
3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or…
In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer…
Neural Radiance Fields (NeRF) show impressive performance for the photorealistic free-view rendering of scenes. However, NeRFs require dense sampling of images in the given scene, and their performance degrades significantly when only a…
We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations. In contrast to…
We propose a method for estimating the 6DoF pose of a rigid object with an available 3D model from a single RGB image. Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the…
Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints…
Recent breakthroughs in Neural Radiance Fields (NeRFs) have sparked significant demand for their integration into real-world 3D applications. However, the varied functionalities required by different 3D applications often necessitate…
The widespread adoption of Neural Radiance Fields (NeRFs) have ensured significant advances in the domain of novel view synthesis in recent years. These models capture a volumetric radiance field of a scene, creating highly convincing,…
We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple…
The neural radiance field (NeRF) achieved remarkable success in modeling 3D scenes and synthesizing high-fidelity novel views. However, existing NeRF-based methods focus more on the make full use of the image resolution to generate novel…
Neural Radiance Fields (NeRF) show impressive performance in photo-realistic free-view rendering of scenes. Recent improvements on the NeRF such as TensoRF and ZipNeRF employ explicit models for faster optimization and rendering, as…
Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function. Though NeRF is able to render complex 3D scenes with view-dependent effects, few efforts have been devoted to exploring its…
Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow…