Papers › Fully Sparse 3D Occupancy Prediction

Fully Sparse 3D Occupancy Prediction

28 Dec 2023arXiv:2312.17118archive 2025-07-28

Haisong Liu, Yang Chen, Haiguang Wang, Zetong Yang, Tianyu Li, Jia Zeng, Li Chen, Hongyang Li, LiMin Wang

Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering from high computational costs. To bridge the gap, we introduce a novel fully sparse occupancy network, termed SparseOcc. SparseOcc initially reconstructs a sparse 3D representation from camera-only inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries. A mask-guided sparse sampling is designed to enable sparse queries to interact with 2D features in a fully sparse manner, thereby circumventing costly dense features or global attention. Additionally, we design a thoughtful ray-based evaluation metric, namely RayIoU, to solve the inconsistency penalty along the depth axis raised in traditional voxel-level mIoU criteria. SparseOcc demonstrates its effectiveness by achieving a RayIoU of 34.0, while maintaining a real-time inference speed of 17.3 FPS, with 7 history frames inputs. By incorporating more preceding frames to 15, SparseOcc continuously improves its performance to 35.1 RayIoU without bells and whistles.

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 24 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 12 samples from 2 repositories, 8 ran (4 with no instrument failure; 4 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mcg-nju/sparseocc officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 8 ran (2 instrument-failed) · 4 unverified report
mcg-nju/sparsebev mentioned on GitHubpytorchMITSyntology: 9 samples, 5 ran (3 instrument-failed) · 4 unverified report
opendrivelab/occnet mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (1 instrument-failed) · 0 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: 16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 8 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
4ran · our draft was wrong
2ran; the contract check could not run
9ran
8unverified

Licence: 1 of the 24 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 3 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.

mcg-nju/sparseocc official repository 12 samples, 8 ran (2 instrument-failed) · 4 unverified
batch_dice_loss in 60 papers models/matcher.py ran Apache-2.0 (permissive) · 483b6b8c81c0b6bb · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, mask_camera:Tensor/1/bool · returned Tensor · level recorded 2026-09-24
batch_sigmoid_ce_loss in 48 papers models/matcher.py ran Apache-2.0 (permissive) · 7e8e2bcfcb2b11e8 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, mask_camera:Tensor/1/float · returned Tensor · level recorded 2026-09-24
compute_scal_loss models/loss_utils.py ran Apache-2.0 (permissive) · 5b38b49212868074 · report fixture: signature pred:Tensor/3/float, gt:Tensor/2/int, class_id:int/0/int, reverse:bool/0/bool, ignore_index:int/0/int · returned tuple · level recorded 2026-09-24
index2point models/sparse_voxel_decoder.py ran Apache-2.0 (permissive) · f87970b7c22e56a5 · report fixture: signature coords:Tensor/3/int, pc_range:list/1/int, voxel_size:float/0/float · returned Tensor · level recorded 2026-09-24
make_sample_points_from_mask models/sparsebev_sampling.py ran Apache-2.0 (permissive) · 4a9cf3011e93f57b · report fixture: signature valid_map:Tensor/5/bool, pc_range:list/1/float, occ_size:list/1/int, num_points:int/0/int, occ_loc:NoneType/0/?, offset:Tensor/1/float · returned Tensor · level recorded 2026-09-24
meshgrid3d gen_instance_info.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c6f233575958bdd3 · report fixture: signature occ_size:tuple/1/int, pc_range:list/1/float · returned Tensor · level recorded 2026-09-24
point2bbox models/sparse_voxel_decoder.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · dc9c1c4a8717a0bf · report fixture: signature coords:Tensor/3/float, box_size:float/0/float · returned Tensor · level recorded 2026-09-24
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
models/sparse_voxel_decoder.py ran Apache-2.0 (permissive) · dac02d544d21142d · report fixture: signature pre_feat:Tensor/3/float, pre_coords:Tensor/3/float, interval:int/0/int · returned tuple · level recorded 2026-09-24
get_voxel_decoder_loss_input models/loss_utils.py unverified Apache-2.0 (permissive) · 9e5b23a1e48e12a1 · report
make_sample_points_from_bbox models/sparsebev_sampling.py unverified Apache-2.0 (permissive) · 9cf47f1cb19afbc9 · report
sampling_4d models/sparsebev_sampling.py unverified Apache-2.0 (permissive) · 88369f6990ec316a · report
mcg-nju/sparsebev community (archive-listed) 9 samples, 5 ran (3 instrument-failed) · 4 unverified
detach_variable in 5 papers models/checkpoint.py ran · our draft was wrong fingerprinted MIT (permissive) · c9aa0bc1f2c95d8c · report fixture: signature inputs:tuple/1/Tensor · returned tuple · level recorded 2026-09-24
evaluate in 514 papers val.py ran MIT (permissive) · 97c6373ac9809717 · report fixture: signature dataset:MockDataset/0/?, results:list/1/dict, epoch:int/0/int · returned dict · level recorded 2026-09-24
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f3855be53d36327d · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-25
pad_multiple models/utils.py ran MIT (permissive) · 3e9c83e1f53e5cdb · report fixture: signature inputs:Tensor/4/float, img_metas:list/1/dict, size_divisor:int/0/int · returned Tensor · level recorded 2026-09-24
rotation_3d_in_axis models/utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 24ed606d1bb9e644 · report fixture: signature points:Tensor/3/float, angles:Tensor/2/float · returned Tensor · level recorded 2026-09-24
checkpoint in 42 papers models/checkpoint.py unverified MIT (permissive) · ac40908e99924f13 · report
checkpoint_sequential models/checkpoint.py unverified MIT (permissive) · 1c35dc9d8a7ecbc3 · report
make_sample_points in 6 papers models/sparsebev_sampling.py unverified MIT (permissive) · 7c1905bfbdc4affc · report
sampling_4d models/sparsebev_sampling.py unverified MIT (permissive) · b65b0ef8ceb0314c · report
opendrivelab/occnet community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
rotz in 12 papers utils/vis.py ran · honoured contract Apache-2.0 (permissive) · a30067af1a83cdf2 · report fixture: signature t:Tensor/0/float · returned Tensor · level recorded 2026-09-24
voxel2points utils/vis.py ran Apache-2.0 (permissive) · 4124214e21574acc · report fixture: signature voxel:Tensor/3/int, voxelSize:list/1/float, range:list/1/float, ignore_labels:list/1/int · returned tuple · level recorded 2026-09-24
voxel_profile utils/vis.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · bd1aa420eb46a2d4 · report fixture: signature voxel:Tensor/2/float, voxel_size:list/1/float · returned Tensor · level recorded 2026-09-24

Tasks

Autonomous DrivingPrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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