We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under controllable poses. Our is developed upon recent neural scene representation rendering works which learn representations geometry appearance only 2D images. While existing demonstrated compelling static scenes playback dynamic scenes, photo-realistic reconstruction with implicit methods, in particular user-controlled novel poses, still difficult. To address this problem, we...

Asynchronously operating event cameras find many applications due to their high dynamic range, vanishingly low motion blur, latency and data bandwidth. The field saw remarkable progress during the last few years, existing event-based 3D reconstruction approaches recover sparse point clouds of scene. However, such sparsity is a limiting factor in cases, especially computer vision graphics, that has not been addressed satisfactorily so far. Accordingly, this paper proposes first approach for...

We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under controllable poses. Our is built upon recent neural scene representation rendering works which learn representations geometry appearance only 2D images. While existing demonstrated compelling static scenes playback dynamic scenes, photo-realistic reconstruction with implicit methods, in particular user-controlled novel poses, still difficult. To address this problem, we utilize...

3D hand pose estimation from monocular videos is a long-standing and challenging problem, which now seeing strong upturn. In this work, we address it for the first time using single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with RGB or depth camera such as high temporal resolution at low data throughputs real-time performance 1000 Hz. Due to different modality of cameras compared...

Novel view synthesis techniques predominantly utilize RGB cameras, inheriting their limitations such as the need for sufficient lighting, susceptibility to motion blur, and restricted dynamic range. In contrast, event cameras are significantly more resilient these but have been less explored in this domain, particularly large-scale settings. Current methodologies primarily focus on front-facing or object-oriented (360-degree view) scenarios. For first time, we introduce 3D Gaussians...

3D hand tracking from a monocular video is very challenging problem due to interactions, occlusions, left-right ambiguity, and fast motion. Most existing methods rely on RGB inputs, which have severe limitations under low-light conditions suffer motion blur. In contrast, event cameras capture local brightness changes instead of full image frames do not the described effects. Unfortunately, image-based techniques cannot be directly applied events significant differences in data modalities....

Volumetric reconstruction of dynamic scenes is an important problem in computer vision. It especially challenging poor lighting and with fast motion. partly due to the limitations RGB cameras: To capture motion without much blur, framerate must be increased, which turn requires more lighting. In contrast, event cameras, record changes pixel brightness asynchronously, are less dependent on lighting, making them suitable for recording We hence propose first method spatiotemporally reconstruct...

3D hand pose estimation from monocular videos is a long-standing and challenging problem, which now seeing strong upturn. In this work, we address it for the first time using single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with RGB or depth camera such as high temporal resolution at low data throughputs real-time performance 1000 Hz. Due to different modality of cameras compared...

3D hand tracking from a monocular video is very challenging problem due to interactions, occlusions, left-right ambiguity, and fast motion. Most existing methods rely on RGB inputs, which have severe limitations under low-light conditions suffer motion blur. In contrast, event cameras capture local brightness changes instead of full image frames do not the described effects. Unfortunately, image-based techniques cannot be directly applied events significant differences in data modalities....

Asynchronously operating event cameras find many applications due to their high dynamic range, vanishingly low motion blur, latency and data bandwidth. The field saw remarkable progress during the last few years, existing event-based 3D reconstruction approaches recover sparse point clouds of scene. However, such sparsity is a limiting factor in cases, especially computer vision graphics, that has not been addressed satisfactorily so far. Accordingly, this paper proposes first approach for...

Photorealistic editing of outdoor scenes from photographs requires a profound understanding the image formation process and an accurate estimation scene geometry, reflectance illumination. A delicate manipulation lighting can then be performed while keeping albedo geometry unaltered. We present NeRF-OSR, i.e., first approach for relighting based on neural radiance fields. In contrast to prior art, our technique allows simultaneous both illumination camera viewpoint using only collection...