Related papers: Geo-Supervised Visual Depth Prediction
In addition to color and textural information, geometry provides important cues for 3D scene reconstruction. However, current reconstruction methods only include geometry at the feature level thus not fully exploiting the geometric…
This paper addresses the importance of full-image supervision for monocular depth estimation. We propose a semi-supervised architecture, which combines both unsupervised framework of using image consistency and supervised framework of dense…
The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates. The entity of interest may be an image, sequence of images, a video,…
Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose…
Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime…
When interacting in a three dimensional world, humans must estimate 3D structure from visual inputs projected down to two dimensional retinal images. It has been shown that humans use the persistence of object shape over motion-induced…
Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2D projection in the image plane, which can introduce…
Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…
Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not…
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.…
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…
Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that have never been seen during training. This renders our…
Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited…
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the…
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal only comes from images themselves, the resolution of…
We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate…
Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known scale ambiguity problem in their predictions. We propose…
3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires multiple input views captured under static conditions. To…
Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis…
Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for…