Related papers: INGeo: Accelerating Instant Neural Scene Reconstru…
Recent advancements in Neural Surface Reconstruction (NSR) have significantly improved multi-view reconstruction when coupled with volume rendering. However, relying solely on photometric consistency in image space falls short of addressing…
Neural implicit surfaces have become an important technique for multi-view 3D reconstruction but their accuracy remains limited. In this paper, we argue that this comes from the difficulty to learn and render high frequency textures with…
Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous…
3D reconstruction from videos has become increasingly popular for various applications, including navigation for autonomous driving of robots and drones, augmented reality (AR), and 3D modeling. This task often combines traditional…
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…
Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they…
Reconstruction of deformable scenes from endoscopic videos is important for many applications such as intraoperative navigation, surgical visual perception, and robotic surgery. It is a foundational requirement for realizing autonomous…
In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently risen to prominence…
Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid,…
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle…
Neural Radiance Fields (NeRFs) have proven to be powerful 3D representations, capable of high quality novel view synthesis of complex scenes. While NeRFs have been applied to graphics, vision, and robotics, problems with slow rendering…
Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of…
We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances…
Online reconstructing and rendering of large-scale indoor scenes is a long-standing challenge. SLAM-based methods can reconstruct 3D scene geometry progressively in real time but can not render photorealistic results. While NeRF-based…
We propose SirenPose, a novel loss function that combines the periodic activation properties of sinusoidal representation networks with geometric priors derived from keypoint structures to improve the accuracy of dynamic 3D scene…
We present a fast and simple technique to convert images into a radiance surface-based scene representation. Building on existing radiance volume reconstruction algorithms, we introduce a subtle yet impactful modification of the loss…
3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. However, its rendering speed and model…
Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across computer vision applications, their potential remains…
Neuromorphic cameras, also known as event cameras, are asynchronous brightness-change sensors that can capture extremely fast motion without suffering from motion blur, making them particularly promising for 3D reconstruction in extreme…
Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed…