相关论文: One View Is Enough! Monocular Training for In-the-…

We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network…

We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, existing approaches rely…

Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome this limitation with a highly scalable self-supervised framework capable of leveraging…

This paper addresses the problem of Monocular Depth Estimation (MDE). Existing approaches on MDE usually model it as a pixel-level regression problem, ignoring the underlying geometry property. We empirically find this may result in…

Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image frame. This paper presents the first study on out-of-view…

Large-scale visuomotor policy learning is a promising approach toward developing generalizable manipulation systems. Yet, policies that can be deployed on diverse embodiments, environments, and observational modalities remain elusive. In…

Multi-view geometry-based methods dominate the last few decades in monocular Visual Odometry for their superior performance, while they have been vulnerable to dynamic and low-texture scenes. More importantly, monocular methods suffer from…

Generating high-quality novel views of a scene from a single image requires maintaining structural coherence across different views, referred to as view consistency. While diffusion models have driven advancements in novel view synthesis,…

Omnidirectional and 360{\deg} images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information…

We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuous nor implicit, challenging recent trends on view…

Solving depth estimation with monocular cameras enables the possibility of widespread use of cameras as low-cost depth estimation sensors in applications such as autonomous driving and robotics. However, learning such a scalable depth…

Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by…

We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of…

Recently, learning-based robotic navigation systems have gained extensive research attention and made significant progress. However, the diversity of open-world scenarios poses a major challenge for the generalization of such systems to…

Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually…

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view…

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions.…

Single-view intrinsic image decomposition is a highly ill-posed problem, and so a promising approach is to learn from large amounts of data. However, it is difficult to collect ground truth training data at scale for intrinsic images. In…

Conventional depth-free multi-view datasets are captured using a moving monocular camera without metric calibration. The scales of camera positions in this monocular setting are ambiguous. Previous methods have acknowledged scale ambiguity…

In this paper, we address the novel, highly challenging problem of estimating the layout of a complex urban driving scenario. Given a single color image captured from a driving platform, we aim to predict the bird's-eye view layout of the…