Related papers: Efficient Visibility Approximation for Game AI usi…
The deployment of humanoid robots for dexterous manipulation in unstructured environments remains challenging due to perceptual limitations that constrain the effective workspace. In scenarios where physical constraints prevent the robot…
The Orientation Distribution Function (ODF) characterizes key brain microstructural properties and plays an important role in understanding brain structural connectivity. Recent works introduced Implicit Neural Representation (INR) based…
This paper aims to tackle the challenge of efficiently producing interactive free-viewpoint videos. Some recent works equip neural radiance fields with image encoders, enabling them to generalize across scenes. When processing dynamic…
Neural distance fields (NDF) have emerged as a powerful tool for addressing challenges in 3D computer vision and graphics downstream problems. While significant progress has been made to learn NDF from various kind of sensor data, a crucial…
In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in…
Beyond novel view synthesis, Neural Radiance Fields are useful for applications that interact with the real world. In this paper, we use them as an implicit map of a given scene and propose a camera relocalization algorithm tailored for…
Dense reconstruction and differentiable rendering are fundamental tightly connected operations in 3D vision and computer graphics. Recent neural implicit representations demonstrate compelling advantages in reconstruction fidelity and…
Photorealistic object appearance modeling from 2D images is a constant topic in vision and graphics. While neural implicit methods (such as Neural Radiance Fields) have shown high-fidelity view synthesis results, they cannot relight the…
Dynamic neural radiance fields (dynamic NeRFs) have demonstrated impressive results in novel view synthesis on 3D dynamic scenes. However, they often require complete video sequences for training followed by novel view synthesis, which is…
Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based…
Autonomous drone racing requires the tight coupling of perception, planning, and control under extreme agility. However, recent approaches typically rely on precomputed spatial reference trajectories or explicit 6-DoF gate pose estimation,…
Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating…
Omnidirectional cameras are extensively used in various applications to provide a wide field of vision. However, they face a challenge in synthesizing novel views due to the inevitable presence of dynamic objects, including the…
The recent research explosion around implicit neural representations, such as NeRF, shows that there is immense potential for implicitly storing high-quality scene and lighting information in compact neural networks. However, one major…
Deep neural networks (DNNs) are widely applied for nowadays 3D surface reconstruction tasks and such methods can be further divided into two categories, which respectively warp templates explicitly by moving vertices or represent 3D…
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an…
We consider outdoor optical access points (OAPs), which, enabled by recent advances in metasurface technology, have attracted growing interest. While OAPs promise high data rates and strong physical-layer security, practical deployments…
Advanced techniques using Neural Radiance Fields (NeRF), Signed Distance Fields (SDF), and Occupancy Fields have recently emerged as solutions for 3D indoor scene reconstruction. We introduce a novel two-phase learning approach, H2O-SDF,…
Global localisation from visual data is a challenging problem applicable to many robotics domains. Prior works have shown that neural networks can be trained to map images of an environment to absolute camera pose within that environment,…
Neural radiance fields (NeRFs) produce state-of-the-art view synthesis results. However, they are slow to render, requiring hundreds of network evaluations per pixel to approximate a volume rendering integral. Baking NeRFs into explicit…