Papers › LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

28 Nov 2023arXiv:2311.17245archive 2025-07-28

Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction, and applies a pruning and recovery process to reduce redundancy while preserving visual quality. Knowledge distillation and pseudo-view augmentation then transfer spherical harmonic coefficients to a lower degree, yielding compact representations. Gaussian Vector Quantization, based on each Gaussian's global significance, further lowers bitwidth with minimal accuracy loss. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework, enabling efficient complex scene representation on the Mip-NeRF 360 and Tank & Temple datasets. The proposed Gaussian pruning approach is also adaptable to other 3D representations (e.g., Scaffold-GS), demonstrating strong generalization capabilities.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of LightGaussian, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='LightGaussian') (how to connect); the free check have('2311.17245') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 22 code samples harvested from 1 repository linked to this paper: 17 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 17 ran (3 with no instrument failure; 14 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VITA-Group/LightGaussian officialmentioned on GitHubpytorchSyntology: 22 samples, 17 ran (14 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

22 samples harvested: 17 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
10ran · our draft was wrong
4ran; the contract check could not run
1ran
5unverified

Licence: 22 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from VITA-Group/LightGaussian. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

VITA-Group/LightGaussian official repository 22 samples, 17 ran (14 instrument-failed) · 5 unverified
CosineSimCodebook in 5 papers vectree/vectree.py ran licence not identified · pointer only · b39d64ccdbec91d0 · report fixture: returned CosineSimCodebook · level recorded 2026-09-22
all_gather_sizes vectree/vectree.py ran · our draft was wrong licence not identified · pointer only · 67e40a826956b6af · report fixture: signature x:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
batched_bincount in 5 papers vectree/vectree.py ran · our draft was wrong licence not identified · pointer only · 6ad4cbc6ce3c3fee · report fixture: signature x:Tensor/2/int, minlength:int/0/int · returned Tensor · level recorded 2026-09-22
batched_embedding vectree/vectree.py ran; the contract check could not run (RAISES) licence not identified · pointer only · afa25690f89377ee · report fixture: signature indices:Tensor/3/int, embeds:Tensor/3/float · returned Tensor · level recorded 2026-09-22
batched_sample_vectors vectree/vectree.py ran · our draft was wrong fingerprinted licence not identified · pointer only · e5404aeba14bc959 · report fixture: signature samples:Tensor/3/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
bin2dec vectree/vectree.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 40526951193cc64d · report fixture: signature b:Tensor/2/float, bits:int/0/int · returned Tensor · level recorded 2026-09-22
dec2bin in 5 papers vectree/vectree.py ran · our draft was wrong licence not identified · pointer only · ffe765a42e1ef688 · report fixture: signature x:Tensor/2/int, bits:int/0/int · returned Tensor · level recorded 2026-09-22
gumbel_noise in 11 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vectree/vectree.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 5eaac03d3e73f0db · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gumbel_sample in 15 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vectree/vectree.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 06047730822c3b0d · report fixture: signature t:Tensor/2/float, temperature:float/0/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
kmeans in 38 papers vectree/vectree.py ran · our draft was wrong licence not identified · pointer only · 633917102614101e · report fixture: signature samples:Tensor/3/float, num_clusters:int/0/int, num_iters:int/0/int, use_cosine_sim:bool/0/bool, sample_fn:callable/0/?, all_reduce_fn:callable/0/? · returned tuple · level recorded 2026-09-22
load_vqgaussian vectree/vectree.py ran · honoured contract licence not identified · pointer only · 87729a4756294a61 · report fixture: signature path:str/0/str, device:str/0/str · returned Tensor · level recorded 2026-09-22
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vectree/vectree.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 0a7e4f0159ab841a · report fixture: signature t:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
orthogonal_loss_fn vectree/vectree.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 3d7ca9943761910a · report fixture: signature t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
read_ply_data vectree/vectree.py ran · honoured contract licence not identified · pointer only · c53d19e40df070b4 · report fixture: signature input_file:str/0/str · returned ndarray · level recorded 2026-09-22
sample_multinomial vectree/vectree.py ran · our draft was wrong licence not identified · pointer only · be04cc927762a6e4 · report fixture: signature total_count:int/0/int, probs:Tensor/1/float · returned Tensor · level recorded 2026-09-22
sample_vectors in 15 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vectree/vectree.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 0fb2b35fef53b5da · report fixture: signature samples:Tensor/2/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
sample_vectors_distributed vectree/vectree.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 6c58c10ecd3f2344 · report fixture: signature local_samples:Tensor/2/float, num:int/0/int · returned Tensor · level recorded 2026-09-22
EuclideanCodebook in 6 papers vectree/vectree.py unverified licence not identified · pointer only · 6370a5cd0634f900 · report
Quantization vectree/vectree.py unverified licence not identified · pointer only · 3e4aaf9361870f33 · report
VectorQuantize in 6 papers vectree/vectree.py unverified licence not identified · pointer only · 6ed4efffd52a2938 · report
uniform_init in 10 papers vectree/vectree.py unverified licence not identified · pointer only · 8bdc31c7c61111b3 · report
write_ply_data vectree/vectree.py unverified licence not identified · pointer only · 1f61a105be5c8959 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for LightGaussian (graph method: LightGaussian), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. calculate_global_significance entry · level 3 · ran · violated contract · 632b8db8bd1b710e3c9d0036d358e2970aff1ec5b7807dbd5cda67151de8bb3d

harvested Assembly for LightGaussian (graph method: LightGaussian). 30 bricks; individually on a fixture: 23 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 3 violated, 1 with no contract checked; 17 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Quantization entry · level 0 · unverified · 3e4aaf9361870f33
  2. VectorQuantize helper · level 0 · unverified · 6ed4efffd52a2938
  3. dec2bin helper · level 1 · ran · our draft was wrong · ffe765a42e1ef688
  4. load_vqgaussian helper · level 1 · ran · honoured contract · 87729a4756294a61
  5. read_ply_data helper · level 1 · ran · honoured contract · c53d19e40df070b4
  6. write_ply_data helper · level 0 · unverified · 1f61a105be5c8959
  7. CosineSimCodebook helper · level 1 · ran · b39d64ccdbec91d0
  8. EuclideanCodebook helper · level 0 · unverified · 6370a5cd0634f900
  9. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  10. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  11. orthogonal_loss_fn helper · level 1 · ran · our draft was wrong · 3d7ca9943761910a
  12. bin2dec helper · level 1 · ran · our draft was wrong · 40526951193cc64d
  13. batched_embedding helper · level 1 · ran; the contract check could not run (RAISES) · afa25690f89377ee
  14. batched_sample_vectors helper · level 1 · ran · our draft was wrong · e5404aeba14bc959
  15. ema_inplace helper · level 0 · unverified · 3aea1727c716b779
  16. gumbel_sample helper · level 1 · ran; the contract check could not run (RAISES) · 06047730822c3b0d
  17. kmeans helper · level 1 · ran · our draft was wrong · 633917102614101e
  18. l2norm helper · level 1 · ran · our draft was wrong · eca6cdf05972a95e
  19. noop helper · level 0 · unverified · 02dd009b7cb924bb
  20. sample_vectors_distributed helper · level 1 · ran; the contract check could not run (RAISES) · 6c58c10ecd3f2344
  21. uniform_init helper · level 0 · unverified · 8bdc31c7c61111b3
  22. laplace_smoothing helper · level 1 · ran · violated contract · b5240484210b398a
  23. sample_vectors helper · level 1 · ran; the contract check could not run (RAISES) · 0fb2b35fef53b5da
  24. gumbel_noise helper · level 1 · ran · our draft was wrong · 5eaac03d3e73f0db
  25. batched_bincount helper · level 1 · ran · our draft was wrong · 6ad4cbc6ce3c3fee
  26. all_gather_sizes helper · level 1 · ran · our draft was wrong · 67e40a826956b6af
  27. all_gather_variably_sized helper · level 1 · ran; the contract check could not run · 2e60cd798dd2182c
  28. sample_multinomial helper · level 1 · ran · our draft was wrong · be04cc927762a6e4
  29. log helper · level 1 · ran · our draft was wrong · 0a7e4f0159ab841a
  30. pad_shape helper · level 1 · ran; the contract check could not run · 64ec7553b1fd0e74

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2311.17245") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Knowledge DistillationNeRFNetwork PruningNeural RenderingNovel View SynthesisQuantizationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Novel View Synthesis Mip-NeRF 360 LightGaussian LPIPS 0.21 #3 of 14 Archive leaderboard report
Novel View Synthesis Mip-NeRF 360 LightGaussian PSNR 28.45 #3 of 14 Archive leaderboard report
Novel View Synthesis Mip-NeRF 360 LightGaussian SSIM 0.857 #3 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Knowledge DistillationPruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections