Related papers: MoAngelo: Motion-Aware Neural Surface Reconstructi…
Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…
The challenge of dynamic view synthesis from dynamic monocular videos, i.e., synthesizing novel views for free viewpoints given a monocular video of a dynamic scene captured by a moving camera, mainly lies in accurately modeling the…
This project presents an exploration into 3D scene reconstruction of synthetic and real-world scenes using Neural Radiance Field (NeRF) approaches. We primarily take advantage of the reduction in training and rendering time of neural…
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video. Unlike previous methods that estimate single-view depth maps separately on each key-frame and fuse them later, we propose to…
While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains a challenge. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) offer powerful…
Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images. Among these, stands out the Neural…
We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation and image-based rendering to the fundamental problem of…
We propose a learning-based method to reconstruct the local terrain for locomotion with a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the algorithm…
Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the…
Triangle meshes are fundamental to 3D applications, enabling efficient modification and rasterization while maintaining compatibility with standard rendering pipelines. However, current automatic mesh generation methods typically rely on…
Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of novel view synthesis (NVS) for its superior performance. In this paper, we propose to synthesize dynamic scenes. Extending the methods for static scenes to dynamic…
Dynamic reconstruction of deformable tissues in endoscopic video is a key technology for robot-assisted surgery. Recent reconstruction methods based on neural radiance fields (NeRFs) have achieved remarkable results in the reconstruction of…
Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems…
We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction…
Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no…
Reconstructing intricate, ever-changing environments remains a central ambition in computer vision, yet existing solutions often crumble before the complexity of real-world dynamics. We present DynaSplat, an approach that extends Gaussian…
Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain incompatible with mesh-based pipelines that power AR/VR and…
3D Gaussian Splatting, known for enabling high-quality static scene reconstruction with fast rendering, is increasingly being applied to multi-view dynamic scene reconstruction. A common strategy involves learning a deformation field to…
We present a method for learning 3D geometry and physics parameters of a dynamic scene from only a monocular RGB video input. To decouple the learning of underlying scene geometry from dynamic motion, we represent the scene as a…
This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly…