Gaussian Splatting for Real-Time Scene Reconstruction: Methods, Systems, and Trade-offs

Ashim Dahal; Rabab Abdelfattah; Nick Rahimi

cs.CVOct 13, 2026

Gaussian Splatting for Real-Time Scene Reconstruction: Methods, Systems, and Trade-offs

Authors: Ashim Dahal, Rabab Abdelfattah, Nick Rahimi

Organizations: School of Computing and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39401, USA

Abstract

3D Gaussian Splatting (3DGS) allows for high-quality real-time novel-view synthesis. Since its inception in 2023, its explicit and highly configurable scene representation has been extended toward sparse-view generation, dynamic reconstruction, efficiency and compression, streaming, and simultaneous localization and mapping (SLAM). Although Gaussian Splatting can provide real-time rendering, rendering an existing representation is distinct from constructing, updating, or maintaining the scene itself. In this survey, we synthesize current literature, categorize them and provide a connection of current approaches and tools towards an end-to-end pipeline. Explicitly, we categorize GS scene reconstruction into five overlapping families: single-shot generation, dynamic representations, efficiency and compression, streaming and immersive systems, and Gaussian Splatting SLAM. We distinguish render-only throughput from task-specific scene generation, update, tracking, mapping, and optimization costs, and combine controlled sparse-view benchmarking with native evaluations to identify cross-family quality, latency, memory, and update-cost trade-offs.

Figures & tables

Survey	Year	Primary organization	Distinctive emphasis
Wu et al. [ 62 ]	2024	Reconstruction, editing, downstream applications	Functional overview of 3DGS developments
Fei et al. [ 10 ]	2025	Characteristics and applications	Theoretical foundations and application taxonomy
Bao et al. [ 2 ]	2025	Optimization, applications, extensions	Technical modules, challenges, and opportunities
Bagdasarian et al. [ 1 ]	2025	Compression and compaction	Representation size and compression efficiency
Zhu et al. [ 80 ]	2024	Robotics applications and technical advances	3DGS for robotic perception and interaction
Ours	2023–2025	Five reconstruction-pipeline families	Task-specific runtime, quantitative evaluation, and deployment trade-offs

Table 1: Positioning of this survey relative to representative Gaussian Splatting surveys.

Figure 1: Overview of a Gaussian Splatting–based reconstruction pipeline. Starting from images/video (optionally RGB-D/events), the system forms pose/geometry cues, initializes Gaussians (one-shot or MVS lifting), updates/optimizes the scene representation (per-scene, online, or temporal), and rasterizes/composites to produce renders, maps, and poses. Shaded containers indicate where the five taxonomy families primarily intervene (single-shot generation, dynamic representations, efficiency/compression, streaming/immersive video, and SLAM with tracking–mapping).

Symbol	Meaning
$I_{i}$ / $I_{t}$	Input image $i$ (or frame at time $t$ ).
$K$	Camera intrinsics matrix.
$T_{i}=(R_{i},t_{i})$	Camera pose (extrinsics) for view $i$ ; rotation $R_{i}$ and translation $t_{i}$ .
$\pi(\cdot)$	Camera projection function mapping 3D to image coordinates.
$\mathbf{u}$	Pixel coordinate in the image plane.
$\mathcal{G}$ / $\mathcal{G}_{t}$	Set of Gaussians for a static scene (or at time $t$ ).

Table 2: Notation used throughout the survey.

Core tags (shared vocabulary)
Input	mono-video; sparse-mv; dense-mv; RGB-D; events+RGB
Pose	known; estimated/refined; pose-free
Depth cue	sensor depth; predicted depth; MVS; none
Regime	PerSeq (per-seq. opt.); PreTr (amortized); HybridR (init+refine)
Temporal scope	static; dynamic
Runtime setting	offline; online; streaming

Table 3: Master tag schema used across the survey. Core tags are shared across all method families; family-specific tags are used only in the corresponding matrices.

Figure 2: Taxonomy of Gaussian Splatting for Real-Time Scene Reconstruction. The diagram categorizes methods into dynamic representations, single-shot generation, efficiency, streaming and immersive video, and SLAM. For a clearer chronological view and additional representative methods from each family, see Figure 3 .

Task	Unit of work	Timing boundary	Metric
Rendering	One rendered frame	Existing representation to rendered frame	rFPS
Scene generation	One fixed input-view set	Input views to Gaussian representation	Scene throughput
Dynamic / streaming	One defined update or transition	Update input to updated representation	Update throughput
SLAM tracking	One input frame	Frame input to pose estimate	Tracking FPS
SLAM mapping	One map update	Mapping input to updated map	Mapping throughput
Offline optimization	One training or optimization run	Start to completed model/checkpoint	Time / iterations

Table 4: Task-specific runtime quantities used in this survey.

Figure 3: Chronological development of representative Gaussian Splatting methods across the five survey families. Methods are positioned by publication year and primary contribution; the figure is representative rather than exhaustive.

Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Model-stage latency (ms) $\downarrow$ Model-stage scene/s $\uparrow$	rFPS $\uparrow$	GPU (GiB) $\downarrow$
MVSplat [ 5 ]	26.78	0.881	0.119	37.63	26.57	871.21	1.18
DepthSplat [ 63 ]	27.62	0.898	0.106	65.37	15.30	654.68	2.63
pixelSplat [ 4 ]	26.40	0.873	0.127	120.57	8.29	462.29	2.77

Table 5: Controlled comparison of single-shot Gaussian reconstruction methods on RealEstate10K [ 78 ] . All methods use the same 100 test scenes, two context views, three target views,

256\times 256

resolution, and an NVIDIA A100 GPU. Model-stage scene latency and scene throughput include the encoder and three target decodes, while rFPS reports decoder-only rendering.

Method	Dataset / input	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Runtime
Splatt3R [ 49 ]	ScanNet++ [ 71 ] , 2 views	–	–	–	1.10 s construction / export
InstantSplat [ 9 ]	T&T Horse [ 23 ] , 3 views	23.30	0.823	0.125	16.01 s initialization + 35.02 s optimization

Table 6: Family-specific measurements for additional single-shot and sparse-view methods. These results use different datasets and execution settings than table 5 and are not directly comparable. Runtime refers to the method-specific measured construction or optimization stages.

Method	Dataset	Schedule	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	rFPS $\uparrow$
4DGaussians [ 61 ]	D-NeRF [ 42 ]	20k	40.81	0.994	0.014 VGG / 0.006 Alex	36.03
Deformable-3D-Gaussians [ 67 ]	D-NeRF [ 42 ]	40k	41.38	0.996	0.008	–
MotionGS [ 79 ]	DyNeRF [ 27 ]	20k	–	–	–	–

Table 7: Native evaluation of dynamic Gaussian representation methods. 4DGaussians and Deformable-3D-Gaussians are evaluated on D-NeRF bouncingballs [ 42 ] ; MotionGS was evaluated on the DyNeRF flame_steak sequence [ 27 ] using its documented schedule but did not complete. Results use method-specific native evaluation procedures and are not a controlled cross-method benchmark.

Method	Dataset	Schedule	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	rFPS $\uparrow$
Octree-GS [ 43 ]	N3DV [ 27 ]	40k	30.42	0.941	0.109	–
3D-GS [ 19 ]	N3DV [ 27 ]	30k	25.01	0.933	0.165	193.46
PUP 3D-GS [ 13 ]	N3DV [ 27 ]	30k + 5k + 5k	25.42	0.930	0.185	155.15
Compact3D [ 35 ]	N3DV [ 27 ]	30k base + 5k fine-tune	25.08	0.916	0.166	–
gsplat [ 70 ]	N3DV [ 27 ]	30k	21.93	0.919	0.208	119.31
SpeedE3DGS [ 54 ]	D-NeRF [ 42 ]	30k	38.59	0.993	0.017	762.25

Table 8: Native evaluation of efficiency and compression methods. Results use method-specific training schedules. Methods evaluated on different datasets or native pipelines are not directly ranked against each other. rFPS is omitted when it is not reported by the native evaluation.

Representation	Size (MiB) $\downarrow$	Gaussians	Size reduction $\uparrow$	PSNR $\uparrow$
3D-GS [ 19 ]	75.50	319,222	–	25.01
PUP 3D-GS [ 13 ]	7.55	31,922	90.00%	25.42
Compact3D [ 35 ]	5.54	–	92.66%	25.08

Table 9: Compression results from the shared 30k vanilla 3D-GS baseline on N3DV flame_steak [ 27 ] . PUP 3D-GS and Compact3D use the same trained baseline, allowing a direct comparison of representation size and retained quality.

Method	Evaluation unit	Schedule	PSNR $\uparrow$	Operation time $\downarrow$	Transition/s $\uparrow$	rFPS $\uparrow$
IGS [ 65 ]	1 transition	100 refinement iter.	33.72	7.41 s	0.116	126.74
3DGStream [ 51 ]	37 transitions	15k init.; 150 + 100/update	27.34 / 28.18	12.63 s/update	0.079	–
GIFStream [ 26 ]	2-frame GOP	30k	28.90	2023.62 s/GOP	–	89.75

Table 10: Native evaluation of streaming and immersive Gaussian methods on N3DV flame_steak [ 27 ] . IGS and 3DGStream measure online transition updates, whereas GIFStream uses offline two-frame GOP optimization.

Method	Input	Frames	Wrapped time (ms/frame) $\downarrow$	Frames/s $\uparrow$	Trajectory error (m) $\downarrow$	Model size (MiB)
MonoGS [ 33 ]	Replica office0, RGB-D	12	2250.57	0.444	0.000082	2.14
RTG-SLAM [ 41 ]	Replica office0, RGB-D	20	884.60	1.130	0.00910	10.35
WildGS-SLAM [ 76 ]	Crowd, monocular	100	1525.64	0.655	0.00665	9.78

Table 11: Native evaluation of Gaussian SLAM systems. MonoGS and RTG-SLAM use Replica office0 [ 50 ] , while WildGS-SLAM uses a monocular Crowd sequence. Processed-frame throughput is measured over the complete wrapped run and should not be interpreted as a controlled ranking across methods.

3D Gaussian Splatting

3D Gaussian Splatting represents scenes as optimizable 3D Gaussian primitives for fast, photorealistic rendering from new viewpoints.

See all 986 papers

SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting
Dec 8, 2025Seokhyun Youn, Soohyun Lee, Geonho Kim +33DGS Compression 3D Gaussian Splatting
Kyung Hee University, South Korea · Kyung Hee University, Seoul, South Korea
EffGS: Efficient and High-Fidelity Gaussian Splatting
Sep 30, 2026Changbai Li, Shuo Yang, Yichen Yang +23D Gaussian Splatting 3D Gaussian Pruning
Beihang University · Nanyang Technological University
ACEsplat: Accelerated 3D Gaussian Scene Regression via RGB and Poses Only
Jun 20, 2026Mingkai Liu, Haohua Que, Dikai Fan +73D Gaussian Splatting Scene Coordinate Regression
Peking University · University of Georgia · Infinity Robotics +3

Dec 8, 2025J/K move · Enter open · S save

SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting

Seokhyun Youn, Soohyun Lee, Geonho Kim, Weeyoung Kwon+2

Kyung Hee University, South Korea · Kyung Hee University, Seoul, South Korea

3DGS Compression 3D Gaussian Splatting Gaussian Splatting Compression Dynamic Scene Reconstruction Gaussian Splatting

Open paper AskPDF arXiv

3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis. However, its practical use is hindered by the massive memory and computational demands required to store and render millions of Gaussians. These challenges become even more severe in 4D dynamic scenes. To address these issues, the field of Efficient Gaussian Splatting has rapidly evolved, proposing methods that reduce redundancy while preserving reconstruction quality. This survey provides the first unified overview of efficient 3D and 4D Gaussian Splatting techniques. For both 3D and 4D settings, we systematically categorize existing methods into two major directions, Parameter Compression and Restructuring Compression, and comprehensively summarize the core ideas and methodological trends within each category. We further cover widely used datasets, evaluation metrics, and representative benchmark comparisons. Finally, we discuss current limitations and outline promising research directions toward scalable, compact, and real-time Gaussian Splatting for both static and dynamic 3D scene representation.

Abstract

3D Gaussian Splatting

Explore similar work

SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting

EffGS: Efficient and High-Fidelity Gaussian Splatting

ACEsplat: Accelerated 3D Gaussian Scene Regression via RGB and Poses Only