Papers › FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes

FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes

28 May 2024arXiv:2405.17958archive 2025-07-28

Yunsong Wang, Tianxin Huang, Hanlin Chen, Gim Hee Lee

Empowering 3D Gaussian Splatting with generalization ability is appealing. However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones, thus lacking the ability to accurately localize 3D Gaussian and support free-view synthesis across wide view range. In this paper, we present a novel framework FreeSplat that is capable of reconstructing geometrically consistent 3D scenes from long sequence input towards free-view synthesis.Specifically, we firstly introduce Low-cost Cross-View Aggregation achieved by constructing adaptive cost volumes among nearby views and aggregating features using a multi-scale structure. Subsequently, we present the Pixel-wise Triplet Fusion to eliminate redundancy of 3D Gaussians in overlapping view regions and to aggregate features observed across multiple views. Additionally, we propose a simple but effective free-view training strategy that ensures robust view synthesis across broader view range regardless of the number of views. Our empirical results demonstrate state-of-the-art novel view synthesis peformances in both novel view rendered color maps quality and depth maps accuracy across different numbers of input views. We also show that FreeSplat performs inference more efficiently and can effectively reduce redundant Gaussians, offering the possibility of feed-forward large scene reconstruction without depth priors.

PaperPDFCodeCode 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 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wangys16/freesplat officialmentioned in papermentioned on GitHubjaxSyntology: 11 samples, 8 ran (2 instrument-failed) · 3 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

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 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 · our draft was wrong
1ran; the contract check could not run
6ran
3unverified

Licence: 11 of the 11 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 wangys16/freesplat. “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.

wangys16/freesplat official repository 11 samples, 8 ran (2 instrument-failed) · 3 unverified
calculate_distance_matrix src/model/encoder/encoder_freesplat.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2e543c366f43eb85 · report fixture: signature poses:Tensor/4/float · returned Tensor · level recorded 2026-09-24
compute_depth_metrics in 5 papers sr_utils/metrics_utils.py ran no licence file found · pointer only · 7bd7020b105681fb · report fixture: signature gt:Tensor/2/float, pred:Tensor/2/float, mult_a:bool/0/bool · returned dict · level recorded 2026-09-24
compute_depth_metrics_batched sr_utils/metrics_utils.py ran no licence file found · pointer only · 8ec9da34a5673745 · report fixture: signature gt_bN:Tensor/2/float, pred_bN:Tensor/2/float, valid_masks_bN:Tensor/2/bool, mult_a:bool/0/bool · returned dict · level recorded 2026-09-24
get_camera_rays sr_utils/geometry_utils.py ran no licence file found · pointer only · 1918629f6ecbec09 · report fixture: signature world_T_cam_b44:Tensor/3/float, world_points_b3N:Tensor/3/float, in_camera_frame:bool/0/bool, cam_T_world_b44:Tensor/3/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
normalize_depth in 6 papers sr_utils/generic_utils.py ran no licence file found · pointer only · 8815d837bbe3d707 · report fixture: signature depth_b1hw:Tensor/4/float, mask_b1hw:Tensor/4/bool, robust:bool/0/bool · returned Tensor · level recorded 2026-09-24
normalize_depth_single sr_utils/generic_utils.py ran no licence file found · pointer only · 748f2268d1a46ec6 · report fixture: signature depth_11hw:Tensor/4/float, mask_11hw:Tensor/4/bool, robust:bool/0/bool · returned Tensor · level recorded 2026-09-24
positional_encoding in 63 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input
src/model/encoder/encoder_freesplat.py ran fingerprinted no licence file found · pointer only · 70593029b8676d40 · report fixture: signature positions:Tensor/2/float, freqs:int/0/int, ori:bool/0/bool · returned Tensor · level recorded 2026-09-24
readlines in 11 papers sr_utils/generic_utils.py ran · our draft was wrong no licence file found · pointer only · 0519b1fecd093fc9 · report fixture: signature filepath:str/0/str · returned list · level recorded 2026-09-24
colormap_image sr_utils/visualization_utils.py unverified no licence file found · pointer only · adb082ec7f229e10 · report
rotation_distance src/model/encoder/encoder_freesplat.py unverified no licence file found · pointer only · 5d1da1b536d8bdff · report
to_homogeneous in 8 papers sr_utils/geometry_utils.py unverified no licence file found · pointer only · 69a7e51abb4506ac · report

Tasks

Novel View Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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