Related papers: Regulating Intermediate 3D Features for Vision-Cen…
Despite the impressive progress of telepresence systems for room-scale scenes with static and dynamic scene entities, expanding their capabilities to scenarios with larger dynamic environments beyond a fixed size of a few square-meters…
Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. However, applying them to autonomous 3D reconstruction, where a robot is…
Volumetric visualization has long been dominated by Direct Volume Rendering (DVR), which operates on dense voxel grids and suffers from limited scalability as resolution and interactivity demands increase. Recent advances in 3D Gaussian…
We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our…
Novel view synthesis has seen significant advancements with 3D Gaussian Splatting (3DGS), enabling real-time photorealistic rendering. However, the inherent fuzziness of Gaussian Splatting presents challenges for 3D scene understanding,…
3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically…
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric…
Video models have recently been applied with success to problems in content generation, novel view synthesis, and, more broadly, world simulation. Many applications in generation and transfer rely on conditioning these models, typically…
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…
Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image…
Recovering the physical attributes of an object's appearance from its images captured under an unknown illumination is challenging yet essential for photo-realistic rendering. Recent approaches adopt the emerging implicit scene…
UAV missions often require specific geometric constraints to be satisfied between ground locations and the vehicle location. Such requirements are typical for contexts where line-of-sight must be maintained between the vehicle location and…
Neural fields can be trained from scratch to represent the shape and appearance of 3D scenes efficiently. It has also been shown that they can densely map correlated properties such as semantics, via sparse interactions from a human…
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…
3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…
Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to…
Recent work has demonstrated that volumetric scene representations combined with differentiable volume rendering can enable photo-realistic rendering for challenging scenes that mesh reconstruction fails on. However, these methods entangle…
The recent increase in popularity of volumetric representations for scene reconstruction and novel view synthesis has put renewed focus on animating volumetric content at high visual quality and in real-time. While implicit deformation…
3D volume rendering is widely used to reveal insightful intrinsic patterns of volumetric datasets across many domains. However, the complex structures and varying scales of volumetric data can make efficiently generating high-quality volume…
The goal of 3D visualization is to provide the user with an intuitive interface which enables him to explore the 3D data in an interactive manner. The aim of the exploration is to identify and analyze anomalies or to give proof of the…