Tag
Flux-GS enables real-time high-fidelity 3D Gaussian Splatting on mobile platforms through efficient lighting representation, attribute-conditioned enhancement, and multi-view densification strategies.
Introduces DF3DV-1K, a large-scale real-world dataset with 1,048 scenes and 89,924 images for distractor-free novel view synthesis, along with a benchmark of nine methods and an application improving radiance field methods via fine-tuning a diffusion-based 2D enhancer.
An agent chained two Hugging Face Spaces—one for image generation and one for 3D reconstruction—to produce a cinematic 3D Paris gallery, illustrating the building-block economy where agents glue together proven components rather than building from scratch.
ABot-Earth 0.5 is a generative 3D framework that synthesizes realistic 3D urban environments from satellite imagery using 3D Gaussian Splatting, enabling real-time visualization and closed-loop UAV navigation at low cost.
ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.
RadianceKit is a Mac app that converts photographs into 3D Gaussian splats for 3D scene reconstruction.
TideGS introduces an out-of-core training framework that enables 3D Gaussian Splatting with over one billion primitives on a single GPU by managing parameters across SSD-CPU-GPU hierarchy via block-virtualization, asynchronous pipeline, and differential streaming techniques.
RT-Splatting introduces a new 3D Gaussian Splatting framework that separates geometric occupancy from optical opacity to improve rendering of semi-transparent specular surfaces with high-fidelity reflections and transmission.
A tutorial on building a simplified 3D Gaussian splatting renderer from scratch in C++ and OpenGL, covering loading and rendering Gaussian splats.
The article highlights the use of 3D Gaussian Splatting technology to create photorealistic, browser-based house tours that eliminate the need for real estate agents and VR hardware. It emphasizes the low cost and open-source nature of the solution built on PlayCanvas.
The article introduces a method using mobile phone scanning and 3D Gaussian Splatting technology to generate realistic 3D models of properties. These models can be viewed in a web browser without VR headsets or apps, significantly reducing costs for property viewing and modeling. It also highlights relevant open-source projects and business opportunities.
SplatWeaver is a feed-forward novel view synthesis framework that dynamically allocates 3D Gaussian primitives based on spatial complexity, improving rendering quality and efficiency over fixed-allocation methods. It leverages cardinality Gaussian experts and a pixel-level routing scheme guided by high-frequency priors to adaptively distribute primitives across complex and smooth scene regions.
GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.
HY-World 2.0 is a multi-modal world model framework that generates high-fidelity 3D Gaussian Splatting scenes from text, images, and videos through specialized modules for panorama generation, trajectory planning, and scene composition, achieving state-of-the-art performance among open-source approaches.
SuperSplat is a free, open-source browser-based editor for inspecting, editing, optimizing, and publishing 3D Gaussian Splats, built on web technologies by PlayCanvas. It requires no installation and is available live at superspl.at/editor.