Related papers: Auto-Rectify Network for Unsupervised Indoor Depth…

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…

Single-view depth estimation from omnidirectional images has gained popularity with its wide range of applications such as autonomous driving and scene reconstruction. Although data-driven learning-based methods demonstrate significant…

Magnetic Resonance Imaging allows high resolution data acquisition with the downside of motion sensitivity due to relatively long acquisition times. Even during the acquisition of a single 2D slice, motion can severely corrupt the image.…

In this work we present a novel approach for single depth map super-resolution. Modern consumer depth sensors, especially Time-of-Flight sensors, produce dense depth measurements, but are affected by noise and have a low lateral resolution.…

Depth estimation plays an important role in the robotic perception system. Self-supervised monocular paradigm has gained significant attention since it can free training from the reliance on depth annotations. Despite recent advancements,…

Transfer learning enables solving a specific task having limited data by using the pre-trained deep networks trained on large-scale datasets. Typically, while transferring the learned knowledge from source task to the target task, the last…

We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by…

Single-view depth estimation refers to the ability to derive three-dimensional information per pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed problem because there are multiple depth solutions that…

We propose DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion (Camera Pose) estimation from monocular image sequences. Due to the nature of 3D scene geometry these three components are coupled.…

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D…

Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of…

Monocular depth estimation from a single image is an ill-posed problem for computer vision due to insufficient reliable cues as the prior knowledge. Besides the inter-frame supervision, namely stereo and adjacent frames, extensive prior…

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be…

Self-supervised monocular depth estimation has been widely studied recently. Most of the work has focused on improving performance on benchmark datasets, such as KITTI, but has offered a few experiments on generalization performance. In…

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in…

Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable depth predictions in textureless or occluded regions due to…

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene…