Related papers: SpecNeRF: Gaussian Directional Encoding for Specul…
Neural Radiance Field (NeRF)-based segmentation methods focus on object semantics and rely solely on RGB data, lacking intrinsic material properties. This limitation restricts accurate material perception, which is crucial for robotics,…
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of…
The reconstruction of 3D objects from calibrated photographs represents a fundamental yet intricate challenge in the domains of computer graphics and vision. Although neural reconstruction approaches based on Neural Radiance Fields (NeRF)…
Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such…
The use of 3D Gaussians as representation of radiance fields has enabled high quality novel view synthesis at real-time rendering speed. However, the choice of optimising the outgoing radiance of each Gaussian independently as spherical…
A spike camera is a specialized high-speed visual sensor that offers advantages such as high temporal resolution and high dynamic range compared to conventional frame cameras. These features provide the camera with significant advantages in…
Neural scene representations achieve high-fidelity rendering by encoding 3D scenes as continuous functions, but their latent spaces are typically implicit and globally entangled, making localized editing and physically grounded manipulation…
We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$^{\circ}$ stereo images. Our model takes advantage of the 360$^{\circ}$ input to observe the entire scene with…
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and…
In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit…
Neural scene representations, such as Neural Radiance Fields (NeRF), are based on training a multilayer perceptron (MLP) using a set of color images with known poses. An increasing number of devices now produce RGB-D(color + depth)…
Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images. However, existing…
Neural Radiance Fields (NeRFs) have emerged as a popular approach for novel view synthesis. While NeRFs are quickly being adapted for a wider set of applications, intuitively editing NeRF scenes is still an open challenge. One important…
Gaussian Splatting is a powerful tool for reconstructing diffuse scenes, but it struggles to simultaneously model specular reflections and the appearance of objects behind semi-transparent surfaces. These specular reflections and…
The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms…
We propose Transmission-Reflection Gaussians (TR-Gaussians), a novel 3D-Gaussian-based representation for high-fidelity rendering of planar transmission and reflection, which are ubiquitous in indoor scenes. Our method combines 3D Gaussians…
Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing…
In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the…
We tackle the ill-posed inverse rendering problem in 3D reconstruction with a Neural Radiance Field (NeRF) approach informed by Physics-Based Rendering (PBR) theory, named PBR-NeRF. Our method addresses a key limitation in most NeRF and 3D…
Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data. However, they often rely on Euclidean distances to construct the input graphs. This assumption can be improbable in many real-world…