Papers › Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion

Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion

18 Mar 2022CVPR 2022 1arXiv:2203.09780archive 2025-07-28

Xiaopei Wu, Liang Peng, Honghui Yang, Liang Xie, Chenxi Huang, Chengqi Deng, Haifeng Liu, Deng Cai

Current LiDAR-only 3D detection methods inevitably suffer from the sparsity of point clouds. Many multi-modal methods are proposed to alleviate this issue, while different representations of images and point clouds make it difficult to fuse them, resulting in suboptimal performance. In this paper, we present a novel multi-modal framework SFD (Sparse Fuse Dense), which utilizes pseudo point clouds generated from depth completion to tackle the issues mentioned above. Different from prior works, we propose a new RoI fusion strategy 3D-GAF (3D Grid-wise Attentive Fusion) to make fuller use of information from different types of point clouds. Specifically, 3D-GAF fuses 3D RoI features from the couple of point clouds in a grid-wise attentive way, which is more fine-grained and more precise. In addition, we propose a SynAugment (Synchronized Augmentation) to enable our multi-modal framework to utilize all data augmentation approaches tailored to LiDAR-only methods. Lastly, we customize an effective and efficient feature extractor CPConv (Color Point Convolution) for pseudo point clouds. It can explore 2D image features and 3D geometric features of pseudo point clouds simultaneously. Our method holds the highest entry on the KITTI car 3D object detection leaderboard, demonstrating the effectiveness of our SFD. Codes are available at https://github.com/LittlePey/SFD.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.09780")

Code

Syntology Ran 5 of 13 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

LittlePey/SFD officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 5 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
4ran
8unverified

Licence: 0 of the 13 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 LittlePey/SFD. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_lidar_in_image_fov LittlePey/SFD/kitti_object.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 47397a2377a470c7 · report
random_flip_along_y LittlePey/SFD/pcdet/datasets/augmentor/augmentor_utils_sfd.py official repository ran Apache-2.0 (permissive) · aa16fbdd4a5afcf1 · report
rotx LittlePey/SFD/kitti_util.py official repository ran fingerprinted Apache-2.0 (permissive) · 8843d80ab666c4e9 · report
roty LittlePey/SFD/kitti_util.py official repository ran fingerprinted Apache-2.0 (permissive) · ae86074e10e1dfd7 · report
rotz LittlePey/SFD/kitti_util.py official repository ran Apache-2.0 (permissive) · 082920adf6e29c94 · report
cfg_from_yaml_file LittlePey/SFD/pcdet/config.py official repository unverified Apache-2.0 (permissive) · 696fe155f9990d38 · report
depth_read LittlePey/SFD/depth_to_lidar.py official repository unverified Apache-2.0 (permissive) · 40c0b7bcfe33fd6d · report
get_corner_loss_lidar LittlePey/SFD/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report
get_global_grid_points_of_roi LittlePey/SFD/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 269fcc858076aa5f · report
get_gridify_iou3d_loss LittlePey/SFD/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · f133fe553902b4ff · report
global_rotation LittlePey/SFD/pcdet/datasets/augmentor/augmentor_utils_sfd.py official repository unverified Apache-2.0 (permissive) · 79d4891f6b00a1cd · report
merge_new_config LittlePey/SFD/pcdet/config.py official repository unverified Apache-2.0 (permissive) · 392c0cf3a1b07b12 · report
random_flip_along_x LittlePey/SFD/pcdet/datasets/augmentor/augmentor_utils_sfd.py official repository unverified Apache-2.0 (permissive) · 00692f8182ba51ca · report

Tasks

3D Object DetectionData AugmentationDepth CompletionObject DetectionVocal Bursts Intensity Predictionobject-detection

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