Related papers: Depth self-supervision for single image novel view…

The task of novel view synthesis aims to generate unseen perspectives of an object or scene from a limited set of input images. Nevertheless, synthesizing novel views from a single image still remains a significant challenge in the realm of…

In this paper, we firstly consider view-dependent effects into single image-based novel view synthesis (NVS) problems. For this, we propose to exploit the camera motion priors in NVS to model view-dependent appearance or effects (VDE) as…

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

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…

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 single-view 3D generative methods have made significant advancements by leveraging knowledge distilled from extensive 3D object datasets. However, challenges persist in the synthesis of 3D scenes from a single view, primarily due to…

View synthesis aims to produce unseen views from a set of views captured by two or more cameras at different positions. This task is non-trivial since it is hard to conduct pixel-level matching among different views. To address this issue,…

Learning based approaches for depth perception are limited by the availability of clean training data. This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition…

Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…

Novel view synthesis aims to generate new view images of a given view image collection. Recent attempts address this problem relying on 3D geometry priors (e.g., shapes, sizes, and positions) learned from multi-view images. However, such…

We present a transformation-grounded image generation network for novel 3D view synthesis from a single image. Instead of taking a 'blank slate' approach, we first explicitly infer the parts of the geometry visible both in the input and…

Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and…

Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not…

Novel view synthesis aims to synthesize new images from different viewpoints of given images. Most of previous works focus on generating novel views of certain objects with a fixed background. However, for some applications, such as virtual…

We review solutions to the problem of depth estimation, arguably the most important subtask in scene understanding. We focus on the single image depth estimation problem. Due to its properties, the single image depth estimation problem is…

Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse…

Self-supervised learning for depth estimation possesses several advantages over supervised learning. The benefits of no need for ground-truth depth, online fine-tuning, and better generalization with unlimited data attract researchers to…

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and…

A significant weakness of most current deep Convolutional Neural Networks is the need to train them using vast amounts of manu- ally labelled data. In this work we propose a unsupervised framework to learn a deep convolutional neural…

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the…