Gaussian splatting
PulseAugur coverage of Gaussian splatting — every cluster mentioning Gaussian splatting across labs, papers, and developer communities, ranked by signal.
- used by Gotit.pub 90%
- uses Simultaneous localization and mapping 90%
- used by ScienceCast 70%
- used by alphaXiv 70%
- competes with Nerf 70%
- used by CORE Recommender 70%
- used by CatalyzeX 70%
- instance of alphaXiv 70%
- instance of Gotit.pub 70%
- developed Simultaneous localization and mapping 70%
- instance of CatalyzeX 70%
- used by Nerf 60%
13 day(s) with sentiment data
-
SplitGaussian framework improves dynamic 3D scene reconstruction
Researchers have introduced SplitGaussian, a new framework designed to improve the reconstruction of dynamic 3D scenes from monocular video. Unlike previous methods that combine static and dynamic scene elements, SplitG…
-
XClipGS method enhances medical volume rendering with exact clipping
Researchers have developed XClipGS, a novel method for exact half-space clipping in medical volume Gaussian splatting. This technique allows for interactive rendering of volumetric medical scans by precisely clipping an…
-
TRACE method optimizes active scene reconstruction trajectories
Researchers have developed TRACE, a novel approach to active scene reconstruction that optimizes sensor trajectories for better information gathering. Unlike previous greedy methods that select the next best view in iso…
-
New CDSeg method transfers 2D image labels to 3D environments
Researchers have introduced CDSeg, a novel method for transferring 2D image segmentation labels to 3D environments. This approach utilizes Gaussian primitives as a renderable carrier, eliminating the need for task-speci…
-
New CLEAR framework unifies 3D Gaussian super-resolution
Researchers have introduced CLEAR, a novel single-stage framework designed to improve sparse-view 3D Gaussian Splatting Super-resolution. This method addresses the limitations of traditional two-stage pipelines by joint…
-
New method enables structured asset creation from 3D Gaussian Splatting scenes
Researchers have developed Manifold-GS, a novel method for creating structured assets from 3D Gaussian Splatting (3DGS) scenes. Unlike traditional 3DGS, Manifold-GS separates appearance opacity from geometric mass and r…
-
Gaussian Splatting research advances across communication, scene compression, and dynamic rendering
Recent research explores advancements in 3D Gaussian Splatting (3DGS) across various applications. GSBF introduces a novel pipeline for environment-aware beamforming in MIMO systems by leveraging 3D Gaussian representat…
-
PanoLess framework reconstructs environments from partial reflective views
Researchers have developed PanoLess, a novel framework utilizing Gaussian splatting to reconstruct surrounding environments from images captured on only one side of a reflective surface. This method leverages surface-al…
-
New framework reconstructs wireless radiance fields in real-time
Researchers have developed CORF-GS, a novel framework for real-time wireless radiance field (WRF) reconstruction. This method integrates optical and radio frequency (RF) data by using a unified Gaussian representation w…
-
PanoLess framework reconstructs environment from partial reflective views
Researchers have developed PanoLess, a novel framework that reconstructs the surrounding environment from images captured on only one side of a reflective surface. This method utilizes surface-aligned 2D Gaussian splats…
-
New LAGS method uses graph learning for efficient 3D drone scene reconstruction
Researchers have developed LAGS, a new method for 3D scene reconstruction using aerial drone imagery. To address inefficiencies in resource allocation, they propose a groupwise heterogeneous graph neural network (GW-HGN…
-
GLAM-SLAM: Real-time Gaussian SLAM for Large-scale Scenes
Researchers have developed GLAM-SLAM, a novel real-time system for large-scale monocular Simultaneous Localization and Mapping (SLAM) using Gaussian splatting. This system addresses limitations of existing methods by em…
-
OmniStyle-INR enables universal style transfer for visual data
Researchers have introduced OmniStyle-INR, a new framework designed for universal and multimodal style transfer across various visual data types. This approach utilizes Implicit Neural Representations (INRs) to handle 2…
-
New 3D Language Field Method Enhances Object Retrieval with Ambiguity Awareness
Researchers have developed SaaF (Scene-specific Ambiguity-aware 3D Language Fields), a new method for interactive object retrieval in real-world scenes using Gaussian Splatting. SaaF addresses limitations in existing 3D…
-
New framework improves Gaussian-based image representation efficiency
Researchers have developed Locality-Aware Density Control (LocoADC), a new framework designed to improve the efficiency of Gaussian-based image representations. LocoADC addresses limitations in existing methods by optim…
-
New A$^2$TG method enhances 3D scene rendering efficiency
Researchers have introduced A$^2$TG, a novel 3D scene representation that improves upon Gaussian Splatting by using adaptive anisotropic textured Gaussians. This method allows for non-uniform texture allocation, alignin…
-
DINO-SLAM enhances neural representations in SLAM systems
Researchers have developed DINO-SLAM, a novel approach that integrates DINO features into Simultaneous Localization and Mapping (SLAM) systems. This method aims to improve both implicit (NeRF) and explicit (Gaussian Spl…
-
New GAINS framework uses foundation models for sparse-view inverse rendering
Researchers have developed GAINS, a novel two-stage framework for inverse rendering that utilizes foundation models to improve material and geometry estimation from sparse multi-view captures. This approach stabilizes t…
-
DP-Splat offers adaptive complexity control for 3D Gaussian Splatting
Researchers have introduced DP-Splat, a novel method for controlling complexity in 3D Gaussian Splatting. This approach utilizes a Dirichlet process prior to allow the number of Gaussian components to adapt to scene com…
-
HyperGS advances video representation with fast, generalizable Gaussian predictions
Researchers have developed HyperGS, a novel feedforward approach that directly predicts Gaussian representations for videos in a single pass, eliminating the need for per-video optimization. This method significantly sp…