A curated list of papers and open-source resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months. If you have any additions or suggestions, feel free to contribute. Additional resources like blog posts, videos, etc. are also welcome.
Update Log:
October 28, 2023:
- Added Utilities Section.
- Added 3DGS Converter for editing 3DGS .ply files in Cloud Compare to Utilities.
- Added Kapture (for bundler to colmap model conversion) and Kapture image cropper script with conversion instructions to Utilities.
October 23, 2023:
- Added python WebGL viewer 2.
- Added Intro to gaussian splatting (and Unity viewer) video blog.
October 21, 2023:
- Added python OpenGL viewer.
- Added typescript WebGPU viewer.
October 20, 2023:
- Made abstracts readable (removed hyphenations).
- Added Windows tutorial.
- Other minor text fixes.
- Added Jupyter notebook viewer.
October 19, 2023:
- Added Github page link for Real-time Photorealistic Dynamic Scene Representation.
- Re-ordered headings.
- Added other unofficial implementations.
- Moved Nerfstudio gsplat and fast: C++/CUDA to Unofficial Implementations.
- Added Nerfstudio, Blender, WebRTC, iOS & Metal viewers.
October 17, 2023:
- GaussianDreamer code released.
- Added Real-time Photorealistic Dynamic Scene Representation.
October 16, 2023:
- Added Deformable 3D Gaussians paper.
- Dynamic 3D Gaussians code released. October 15, 2023: Initial list with first 6 papers.
Authors: Bernhard Kerbl, Georgios Kopanas, Thomas LeimkΓΌhler, George Drettakis
Abstract
Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (β₯ 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows real-time rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.π Paper (Low Resolution) | π Paper (High Resolution) | π Project Page | π» Code | π₯ Short Presentation | π₯ Explanation Video
Authors: Jonathon Luiten, Georgios Kopanas, Bastian Leibe, Deva Ramanan
Abstract
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree- of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians which are optimized to reconstruct input images via differentiable rendering. To model dynamic scenes, we al- low Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size. By regularizing Gaussiansβ motion and rotation with local-rigidity constraints, we show that our Dynamic 3D Gaussians correctly model the same area of physical space over time, including the rotation of that space. Dense 6-DOF tracking and dynamic reconstruction emerges naturally from persistent dynamic view synthesis, without requiring any correspondence or flow as input. We demonstrate a large number of downstream applications enabled by our representation, including first-person view synthesis, dynamic compositional scene synthesis, and 4D video editing.π Paper | π Project Page | π» Code | π₯ Explanation Video
Authors: Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, Xiaogang Jin
Abstract
Implicit neural representation has opened up new avenues for dynamic scene reconstruction and rendering. Nonetheless, state-of-the-art methods of dynamic neural rendering rely heavily on these implicit representations, which frequently struggle with accurately capturing the intricate details of objects in the scene. Furthermore, implicit methods struggle to achieve real-time rendering in general dynamic scenes, limiting their use in a wide range of tasks. To address the issues, we propose a deformable 3D Gaussians Splatting method that reconstructs scenes using explicit 3D Gaussians and learns Gaussians in canonical space with a deformation field to model monocular dynamic scenes. We also introduced a smoothing training mechanism with no extra overhead to mitigate the impact of inaccurate poses in real datasets on the smoothness of time interpolation tasks. Through differential gaussian rasterization, the deformable 3D Gaussians not only achieve higher rendering quality but also real-time rendering speed. Experiments show that our method outperforms existing methods significantly in terms of both rendering quality and speed, making it well-suited for tasks such as novel-view synthesis, time synthesis, and real-time rendering.π Paper | π Project Page | π» Code (to be released)
Authors: Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Tian Qi, Xinggang Wang
Abstract
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to maintain. We introduce the 4D Gaussian Splatting (4D-GS) to achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency. An efficient deformation field is constructed to model both Gaussian motions and shape deformations. Different adjacent Gaussians are connected via a HexPlane to produce more accurate position and shape deformations. Our 4D-GS method achieves real-time rendering under high resolutions, 70 FPS at a 800Γ800 resolution on an RTX 3090 GPU, while maintaining comparable or higher quality than previous state-of-the-art method.π Paper | π Project Page | π» Code
Abstract
Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial and temporal structure of dynamic scenes from directly learning the complex 6D plenoptic function. (ii) Scaling Deformation Modeling: Explicitly modeling scene element deformation becomes impractical for complex dynamics. To address these issues, we consider the spacetime as an entirety and propose to approximate the underlying spatio-temporal 4D volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Learning to optimize the 4D primitives enables us to synthesize novel views at any desired time with our tailored rendering routine. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics. This approach offers simplicity, flexibility for variable-length video and end-to-end training, and efficient real-time rendering, making it suitable for capturing complex dynamic scene motions. Experiments across various benchmarks, including monocular and multi-view scenarios, demonstrate our 4DGS model's superior visual quality and efficiency.π Paper | π» Code (to be released)
Authors: Zilong Chen, Feng Wang, Huaping Liu
Abstract
In this paper, we present Gaussian Splatting based text-to-3D generation (GSGEN), a novel approach for generating high-quality 3D objects. Previous methods suffer from inaccurate geometry and limited fidelity due to the absence of 3D prior and proper representation. We leverage 3D Gaussian Splatting, a recent state-of-the-art representation, to address existing shortcomings by exploiting the explicit nature that enables the incorporation of 3D prior. Specifically, our method adopts a pro- gressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage. In geometry optimization, a coarse representation is established under a 3D geometry prior along with the ordinary 2D SDS loss, ensuring a sensible and 3D-consistent rough shape. Subsequently, the obtained Gaussians undergo an iterative refinement to enrich details. In this stage, we increase the number of Gaussians by compactness-based densification to enhance continuity and improve fidelity. With these designs, our approach can generate 3D content with delicate details and more accurate geometry. Extensive evaluations demonstrate the effectiveness of our method, especially for capturing high-frequency components.π Paper | π Project Page | π» Code | π₯ Short Presentation | π₯ Explanation Video
Authors: Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, Gang Zeng
Abstract
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.π Paper | π Project Page | π» Code | π₯ Explanation Video
Authors: Taoran Yi1, Jiemin Fang, Guanjun Wu1, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Tian Qi, Xinggang Wang
Abstract
In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but the 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides point cloud priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance within 25 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time.π Paper | π Project Page | π» Code
- Taichi 3D Gaussian Splatting
- Gaussian Splatting 3D
- 3D Gaussian Splatting
- fast: C++/CUDA
- nerfstudio: python/CUDA
- WebGL Viewer 1
- WebGL Viewer 2
- WebGPU Viewer 1
- WebGPU Viewer 2
- Three.js
- A-Frame
- Nerfstudio Unofficial
- Nerfstudio Viser
- Blender (Editor)
- WebRTC viewer
- iOS & Metal viewer
- jupyter notebook
- python OpenGL viewer
- PlayCanvas Viewer
- 3DGS Converter for editing 3DGS .ply files in Cloud Compare
- Kapture (for bundler to colmap model conversion)
- Kapture image cropper script and conversion instructions
- Gaussian Splatting is pretty cool
- Making Gaussian Splats smaller
- Making Gaussian Splats more smaller
- Introduction to 3D Gaussian Splatting
- Getting Started with 3DGS for Windows
- How to view 3DGS Scenes in Unity
- Two-minute explanation of 3DGS
- Jupyter notebook tutorial
- Intro to gaussian splatting (and Unity plugin)
- Thanks to Leonid Keselman for informing me about the release of the paper "Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting".
- Thanks to Eric Haines for suggesting the jupyter notebook viewer, windows tutorial and for fixing text hyphenations and other issues.
- Thanks to Henry Pearce for adding more resources and debugging the video links.