We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Instead, we build on the intuition that the face region and eyeballs are separate 3D structures that move in a coordinated yet independent fashion. Our method leverages recent advancements in conditional image-based neural radiance fields and proposes a two-stream architecture that predicts volumetric features for the face and eye regions separately. Rigidly transforming the eye features via a 3D rotation matrix provides fine-grained control over the desired gaze angle. The final, redirected image is then attained via differentiable volume compositing. Our experiments show that this architecture outperforms naively conditioned NeRF baselines as well as previous state-of-the-art 2D gaze redirection methods in terms of redirection accuracy and identity preservation. Code and models will be released for research purposes.@en

Despite the recent development of learning-based gaze estimation methods, most methods require one or more eye or face region crops as inputs and produce a gaze direction vector as output. Cropping results in a higher resolution in the eye regions and having fewer confounding factors (such as clothing and hair) is believed to benefit the final model performance. However, this eye/face patch cropping process is expensive, erroneous, and implementation-specific for different methods. In this paper, we propose a frame-to-gaze network that directly predicts both 3D gaze origin and 3D gaze direction from the raw frame out of the camera without any face or eye cropping. Our method demonstrates that direct gaze regression from the raw downscaled frame, from FHD/HD to VGA/HVGA resolution, is possible despite the challenges of having very few pixels in the eye region. The proposed method achieves comparable results to state-of-the-art methods in Point-of-Gaze (PoG) estimation on three public gaze datasets: GazeCapture, MPIIFaceGaze, and EVE, and generalizes well to extreme camera view changes.@en

This paper presents a distributed method for formation control of a homogeneous team of aerial or ground mobile robots navigating in environments with static and dynamic obstacles. Each robot in the team has a finite communication and visibility radius and shares information with its neighbors to coordinate. Our approach leverages both constrained optimization and multi-robot consensus to compute the parameters of the multi-robot formation. This ensures that the robots make progress and avoid collisions with static and moving obstacles. In particular, via distributed consensus, the robots compute (a) the convex hull of the robot positions, (b) the desired direction of movement and (c) a large convex region embedded in the four dimensional position-time free space. The robots then compute, via sequential convex programming, the locally optimal parameters for the formation to remain within the convex neighborhood of the robots. The method allows for reconfiguration. Each robot then navigates towards its assigned position in the target collision-free formation via an individual controller that accounts for its dynamics. This approach is efficient and scalable with the number of robots. We present an extensive evaluation of the communication requirements and verify the method in simulations with up to sixteen quadrotors. Lastly, we present experiments with four real quadrotors flying in formation in an environment with one moving human.

@en

We propose a real-time method for the infrastructure-free estimation of articulated human motion. The approach leverages a swarm of camer aequipped flying robots and jointly optimizes the swarm's and skeletal states, which include the 3D joint positions and a set of bones. Our method allows to track the motion of human subjects, for example an athlete, over long time horizons and long distances, in challenging settings and at large scale, where fixed infrastructure approaches are not applicable. The proposed algorithm uses active infra-red markers, runs in real-time and accurately estimates robot and human pose parameters online without the need for accurately calibrated or stationary mounted cameras. Our method i) estimates a global coordinate frame for the MAV swarm, ii) jointly optimizes the human pose and relative camera positions, and iii) estimates the length of the human bones. The entire swarm is then controlled via a model predictive controller to maximize visibility of the subject from multiple viewpoints even under fast motion such as jumping or jogging. We demonstrate our method in a number of difficult scenarios including capture of long locomotion sequences at the scale of a triplex gym, in non-planar terrain, while climbing and in outdoor scenarios. CCS Concepts: • Computing methodologies → Motion capture; Reconstruction; Robotic planning; Motion path planning;.

@en

In this letter, we propose an algorithm for the training of neural network control policies for quadrotors. The learned control policy computes control commands directly from sensor inputs and is, hence, computationally efficient. An imitation learning algorithm produces a policy that reproduces the behavior of a supervisor. The supervisor provides demonstrations of path following and collision avoidance maneuvers. Due to the generalization ability of neural networks, the resulting policy performs local collision avoidance, while following a global reference path. The algorithm uses a time-free model-predictive path-following controller as a supervisor. The controller generates demonstrations by following few example paths. This enables an easy-to-implement learning algorithm that is robust to errors of the model used in the model-predictive controller. The policy is trained on the real quadrotor, which requires collision-free exploration around the example path. An adapted version of the supervisor is used to enable exploration. Thus, the policy can be trained from a relatively small number of examples on the real quadrotor, making the training sample efficient@en

We propose a method for real-time trajectory generation with applications in aerial videography. Taking framing objectives, such as position of targets in the image plane, as input, our method solves for robot trajectories and gimbal controls automatically and adapts plans in real time due to changes in the environment. We contribute a real-time receding horizon planner that autonomously records scenes with moving targets, while optimizing for visibility under occlusion and ensuring collision-free trajectories. A modular cost function, based on the reprojection error of targets, is proposed that allows for flexibility and artistic freedom and is well behaved under numerical optimization. We formulate the minimization problem under constraints as a finite horizon optimal control problem that fulfills aesthetic objectives, adheres to nonlinear model constraints of the filming robot and collision constraints with static and dynamic obstacles and can be solved in real time. We demonstrate the robustness and efficiency of the method with a number of challenging shots filmed in dynamic environments including those with moving obstacles and shots with multiple targets to be filmed simultaneously.@en

We propose a method for automated aerial videography in dynamic and cluttered environments. An online receding horizon optimization formulation facilitates the planning process for novices and experts alike. The algorithm takes high-level plans as input, which we dub virtual rails, alongside interactively defined aesthetic framing objectives and jointly solves for 3D quadcopter motion plans and associated velocities. The method generates control inputs subject to constraints of a non-linear quadrotor model and dynamic constraints imposed by actors moving in an a priori unknown way. The output plans are physically feasible, for the horizon length, and we apply the resulting control inputs directly at each time-step, without requiring a separate trajectory tracking algorithm. The online nature of the method enables incorporation of feedback into the planning and control loop, makes the algorithm robust to disturbances. Furthermore, we extend the method to include coordination between multiple drones to enable dynamic multi-view shots, typical for action sequences and live TV coverage. The algorithm runs in real-time on standard hardware and computes motion plans for several drones in the order of milliseconds. Finally, we evaluate the approach qualitatively with a number of challenging shots, involving multiple drones and actors and qualitatively characterize the computational performance experimentally.

@en