相关论文: Local Light Field Fusion: Practical View Synthesis…

Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep…

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…

In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes. In our approach, a 3D scene is represented as a light field, i.e., a set of rays, each of which has a corresponding color…

Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency. In order to improve the…

Many popular tourist landmarks are captured in a multitude of online, public photos. These photos represent a sparse and unstructured sampling of the plenoptic function for a particular scene. In this paper,we present a new approach to…

We tackle a new problem of semantic view synthesis -- generating free-viewpoint rendering of a synthesized scene using a semantic label map as input. We build upon recent advances in semantic image synthesis and view synthesis for handling…

Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and…

Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made on enhancing rendering quality and accelerating rendering speed in…

In this work, we present a novel learning-based approach to synthesize new views of a light field image. In particular, given the four corner views of a light field, the presented method estimates any in-between view. We use three…

With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in…

We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene. Recent approaches are computationally expensive, require per-scene optimization, or produce a memory-expensive…

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…

Novel view synthesis of remote sensing scenes is of great significance for scene visualization, human-computer interaction, and various downstream applications. Despite the recent advances in computer graphics and photogrammetry technology,…

Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. Existing methods…

This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from…

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…

Predicting novel views of a scene from real-world images has always been a challenging task. In this work, we propose a deep convolutional neural network (CNN) which learns to predict novel views of a scene from given collection of images.…

We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints. We approach this as a learning task but, critically, instead of learning to…

Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input. In this paper, we…