Papers › Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

6 Dec 2023CVPR 2024 1arXiv:2312.03203archive 2025-07-28

Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi

3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artifacts reducing feature quality. Recently, 3D Gaussian Splatting has shown state-of-the-art performance on real-time radiance field rendering. In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation. This translation is not straightforward: naively incorporating feature fields in the 3DGS framework encounters significant challenges, notably the disparities in spatial resolution and channel consistency between RGB images and feature maps. We propose architectural and training changes to efficiently avert this problem. Our proposed method is general, and our experiments showcase novel view semantic segmentation, language-guided editing and segment anything through learning feature fields from state-of-the-art 2D foundation models such as SAM and CLIP-LSeg. Across experiments, our distillation method is able to provide comparable or better results, while being significantly faster to both train and render. Additionally, to the best of our knowledge, we are the first method to enable point and bounding-box prompting for radiance field manipulation, by leveraging the SAM model. Project website at: https://feature-3dgs.github.io/

PaperPDFConference PDFCodeCode Syntology ran

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.

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

Code

Syntology 24 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 23 samples from 1 repository, 18 ran (10 with no instrument failure; 8 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 between 2026-09-22 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ShijieZhou-UCLA/feature-3dgs officialmentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
keloee/maskfield mentioned on GitHubjaxMITSyntology: 23 samples, 18 ran (8 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

24 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 9 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
5ran; the contract check could not run
8ran
5unverified

Licence: 12 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

ShijieZhou-UCLA/feature-3dgs official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_legend_patch encoders/lseg_encoder/encode_images.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 826d97f0a222f986 · report fixture: signature npimg:ndarray/2/int, new_palette:list/1/int, labels:dict/0/? · returned tuple · level recorded 2026-09-22
keloee/maskfield community (archive-listed) 23 samples, 18 ran (8 instrument-failed) · 5 unverified
OctreeRender_trilinear_fast in 11 papers renderer.py ran MIT (permissive) · 6a37a8e809bde7a0 · report fixture: signature rays:Tensor/2/float, tensorf:callable/0/?, chunk:int/0/int, N_samples:int/0/int, ndc_ray:bool/0/bool, white_bg:bool/0/bool, is_train:bool/0/bool, render_feature:bool/0/bool, out_rgb:bool/0/bool, out_mask:NoneType/0/?, device:str/0/str · returned tuple · level recorded 2026-09-24
OctreeRender_trilinear_fast_depth renderer.py ran MIT (permissive) here; the stored copy is pointer only · eae018b803b70a00 · report fixture: signature rays:Tensor/2/float, tensorf:callable/0/?, chunk:int/0/int, N_samples:int/0/int, ndc_ray:bool/0/bool, is_train:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-24
apply_float_colormap colormaps.py ran MIT (permissive) here; the stored copy is pointer only · 72f9a57ae3d0ae8d · report fixture: signature image:Tensor/3/float, colormap:str/0/str · returned Tensor · level recorded 2026-09-25
batch_dice_loss in 60 papers models/matcher.py ran · our draft was wrong fingerprinted MIT (permissive) · b73525bcfb4b4e5a · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float · returned Tensor · level recorded 2026-09-24
batch_sigmoid_focal_loss in 10 papers models/matcher.py ran MIT (permissive) · 5ce0a97aafc3b0d4 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
models/losses.py ran fingerprinted MIT (permissive) · 016dba4163da28df · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:int/0/int · returned Tensor · level recorded 2026-09-24
eval_sh in 22 papers models/sh.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · db95ecdf5d4abe6b · report fixture: signature deg:int/0/int, sh:Tensor/3/float, dirs:Tensor/2/float · returned Tensor · level recorded 2026-09-24
eval_sh_bases in 17 papers models/sh.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · caa9e209a9083a0f · report fixture: signature deg:int/0/int, dirs:Tensor/2/float · returned Tensor · level recorded 2026-09-22
filter in 20 papers extract_feature.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 2e7f3dd0cf98f11e · report fixture: signature keep:Tensor/1/float, masks_result:list/1/Tensor · returned list · level recorded 2026-09-22
get_color in 28 papers colors.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · eeee61bc904ad6c5 · report fixture: returned Tensor · level recorded 2026-09-27
init_log in 16 papers funcs.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · dc510fe4f2261490 · report fixture: signature log:dict/0/?, keys:list/1/str · returned dict · level recorded 2026-09-24
js_divergence in 12 papers models/losses.py ran fingerprinted MIT (permissive) · 8814888ea31454d6 · report fixture: signature P:Tensor/2/float, Q:Tensor/2/float · returned Tensor · level recorded 2026-09-24
mask_nms extract_feature.py ran MIT (permissive) · d4b16e8ecb449d48 · report fixture: signature masks:Tensor/3/bool, scores:Tensor/1/float, iou_thr:float/0/float, score_thr:float/0/float, inner_thr:float/0/float · returned Tensor · level recorded 2026-09-24
pad_img in 6 papers extract_feature.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · f062653540840f44 · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-22
positional_encoding in 63 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/tensorBase.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 11a10efa60767162 · report fixture: signature positions:Tensor/2/float, freqs:int/0/int · returned Tensor · level recorded 2026-09-22
raw2alpha in 17 papers models/tensorBase.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c1acffa981204fee · report fixture: signature sigma:Tensor/2/float, dist:Tensor/2/float · returned tuple · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
models/losses.py ran fingerprinted MIT (permissive) · 71e149dc0c33b040 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-26
visualize_depth_numpy in 14 papers funcs.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · c775698c33cfa2de · report fixture: signature depth:ndarray/2/float, minmax:NoneType/0/?, cmap:int/0/int · returned tuple · level recorded 2026-09-24
SHRender in 11 papers models/tensorBase.py unverified MIT (permissive) here; the stored copy is pointer only · 3a530f556e40d9c0 · report
chunk_cosine_sim models/matcher.py unverified MIT (permissive) · 88f81a32c328085d · report
evaluation in 57 papers renderer.py unverified MIT (permissive) · 0b4c49066bad50f8 · report
py_sigmoid_focal_loss models/focal_loss.py unverified MIT (permissive) · 2da4941aadc1be82 · report
weight_reduce_loss in 61 papers models/focal_loss.py unverified MIT (permissive) · 0b78c3cf1e82d884 · report

Tasks

3D scene Editing3DGSNatural Language QueriesNeRFNovel View SynthesisSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AWARESAMSPEED

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