REVIEW 9 cited by
gsplat: An Open-Source Library for Gaussian Splatting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
gsplat is an open-source library designed for training and developing Gaussian Splatting methods. It features a front-end with Python bindings compatible with the PyTorch library and a back-end with highly optimized CUDA kernels. gsplat offers numerous features that enhance the optimization of Gaussian Splatting models, which include optimization improvements for speed, memory, and convergence times. Experimental results demonstrate that gsplat achieves up to 10% less training time and 4x less memory than the original implementation. Utilized in several research projects, gsplat is actively maintained on GitHub. Source code is available at https://github.com/nerfstudio-project/gsplat under Apache License 2.0. We welcome contributions from the open-source community.
Forward citations
Cited by 9 Pith papers
-
The Role of Initialization in 3D Gaussian Splatting
Dense initialization of 3DGS does not consistently beat sparse SfM initialization for standard novel views, but improves off-trajectory generalization; no densification method wins everywhere.
-
GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field
A 2D Gaussian video representation with a tri-plane plus polynomial deformation field decodes at 800+ FPS on Bunny and trains in about 2 seconds per frame.
-
Masks make discriminative models great again!
Training a single-image 3D Gaussian splat model on visible regions only, using visibility masks from optimized per-scene splats, improves reconstruction quality in visible areas and stays competitive with full-scene models.
-
Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
A hybrid invertible-network distortion field plus cubemap rendering lets Gaussian Splatting reconstruct scenes from uncalibrated fisheye photos, outperforming prior fisheye methods and reducing the number of captures needed.
-
Fast Wave-optics Rendering of Multiplane Images for 3D Holographic Displays
A new CGH pipeline converts multiplane-image stacks into random-phase holograms with wave-optics alpha compositing, matching Gaussian-based hologram quality while being orders of magnitude faster.
-
InstantSfM: Towards GPU-Native SfM for the Deep Learning Era
A fully GPU-native, PyTorch-based global Structure-from-Motion pipeline using sparse-aware Levenberg-Marquardt with optional metric depth priors reports ~8-40× speedups over COLMAP at comparable accuracy on several be...
-
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
GMC learns per-point SE(3) mappings into a shared canonical space to interpolate and extrapolate 3D point-based scenes under large motion, outperforming baselines that assume small motion.
-
GSCodec Studio: A Modular Framework for Gaussian Splat Compression
GSCodec Studio is a modular open-source framework for Gaussian Splat compression, and its composed Static and Dynamic GSCodec pipelines report competitive rate-distortion results against several baselines.
-
Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction
A 3D Gaussian Splatting framework for urban scenes that combines visibility-based data partitioning, budgeted level-of-detail generation, and per-Gaussian appearance embeddings to enable efficient training and real-ti...
Discussion (0). Continue with ORCID to comment.