Related papers: Self-supervised Wide Baseline Visual Servoing via …

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach…

One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a…

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted…

We present KOVIS, a novel learning-based, calibration-free visual servoing method for fine robotic manipulation tasks with eye-in-hand stereo camera system. We train the deep neural network only in the simulated environment; and the trained…

Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect. Various weakly or self supervised pose estimation methods have been proposed due to lack of 3D data. Nevertheless, these…

We present a novel data-driven regularizer for weakly-supervised learning of 3D human pose estimation that eliminates the drift problem that affects existing approaches. We do this by moving the stereo reconstruction problem into the loss…

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…

Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty.…

We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we…

Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise…

In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

We introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the Next Best View problem (NBV), where one has to identify where to move…

Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent…

Developing gaze estimation models that generalize well to unseen domains and in-the-wild conditions remains a challenge with no known best solution. This is mostly due to the difficulty of acquiring ground truth data that cover the…

Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of…

We propose a method to train deep networks to decompose videos into 3D geometry (camera and depth), moving objects, and their motions, with no supervision. We build on the idea of view synthesis, which uses classical camera geometry to…

We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a…

Unmanned Aerial Vehicle (UAV) Cross-View Geo-Localization (CVGL) presents significant challenges due to the view discrepancy between oblique UAV images and overhead satellite images. Existing methods heavily rely on the supervision of…