Related papers: Artificial Microsaccade Compensation: Stable Visio…
Temporal 3D human pose estimation from monocular videos is a challenging task in human-centered computer vision due to the depth ambiguity of 2D-to-3D lifting. To improve accuracy and address occlusion issues, inertial sensor has been…
Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce…
The development of aerial autonomy has enabled aerial robots to fly agilely in complex environments. However, dodging fast-moving objects in flight remains a challenge, limiting the further application of unmanned aerial vehicles (UAVs).…
Rendering the visual appearance of moving humans from occluded monocular videos is a challenging task. Most existing research renders 3D humans under ideal conditions, requiring a clear and unobstructed scene. Those methods cannot be used…
We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by…
Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while collecting large-scale data is costly and limited demonstrations may lead to localization…
Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we…
Deep learning-based visual perception models lack robustness when faced with camera motion perturbations in practice. The current certification process for assessing robustness is costly and time-consuming due to the extensive number of…
Gaze stabilization is an important requisite for humanoid robots. Previous work on this topic has focused on the integration of inertial and visual information. Little attention has been given to a third component, which is the knowledge…
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this…
This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles. Different from previous sky editing methods…
We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing. It leverages a simple decomposition of the video editing problem into image editing followed by motion-conditioned image animation. Furthermore, given the…
In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often…
This paper presents a novel software-based approach to stabilizing the acoustic images for in-air 3D sonars. Due to uneven terrain, traditional static beamforming techniques can be misaligned, causing inaccurate measurements and imaging…
Optical aberrations prevent telescopes from reaching their theoretical diffraction limit. Once estimated, these aberrations can be compensated for using deformable mirrors in a closed loop. Focal plane wavefront sensing enables the…
Tourists and Wild-life photographers are often hindered in capturing their cherished images or videos by a fence that limits accessibility to the scene of interest. The situation has been exacerbated by growing concerns of security at…
Video generation has recently made striking visual progress, but maintaining coherent object motion and interactions remains difficult. We trace two practical bottlenecks: (i) human-provided motion hints (e.g., small 2D maps) often collapse…
Eye movements are a behavioral response that can be involved in tasks as complicated as natural image classification. This report confirms that pro- and anti-saccades can be used by a volunteer to designate target (animal) or non-target…
Ultra-high-resolution 360-degree video streaming is severely constrained by the massive bandwidth required to deliver immersive experiences. Current viewport prediction techniques predominately rely on kinematics or low-level visual…
Perception systems for ornithopters face severe challenges. The harsh vibrations and abrupt movements caused during flapping are prone to produce motion blur and strong lighting condition changes. Their strict restrictions in weight, size,…