Papers › HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

26 Feb 2024CVPR 2024 1arXiv:2402.17062archive 2025-07-28

Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis

Human hands are highly articulated and versatile at handling objects. Jointly estimating the 3D poses of a hand and the object it manipulates from a monocular camera is challenging due to frequent occlusions. Thus, existing methods often rely on intermediate 3D shape representations to increase performance. These representations are typically explicit, such as 3D point clouds or meshes, and thus provide information in the direct surroundings of the intermediate hand pose estimate. To address this, we introduce HOISDF, a Signed Distance Field (SDF) guided hand-object pose estimation network, which jointly exploits hand and object SDFs to provide a global, implicit representation over the complete reconstruction volume. Specifically, the role of the SDFs is threefold: equip the visual encoder with implicit shape information, help to encode hand-object interactions, and guide the hand and object pose regression via SDF-based sampling and by augmenting the feature representations. We show that HOISDF achieves state-of-the-art results on hand-object pose estimation benchmarks (DexYCB and HO3Dv2). Code is available at https://github.com/amathislab/HOISDF

PaperPDFConference PDFCodeCode 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.

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

Code

Syntology 23 code samples harvested from 1 repository linked to this paper: 16 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 16 ran (8 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

amathislab/hoisdf officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 16 ran (8 instrument-failed) · 7 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

23 samples harvested: 16 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 7 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.

8ran · our draft was wrong
8ran
7unverified

Licence: 23 of the 23 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 amathislab/hoisdf. “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.

amathislab/hoisdf official repository 23 samples, 16 ran (8 instrument-failed) · 7 unverified
JointHeatmapLoss main/model.py ran fingerprinted no licence file found · pointer only · 57de234ead12cd0d · report fixture: signature joint_out:Tensor/2/float, joint_gt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
MLP in 375 papers main/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 15aa4edbfab28f4d · report fixture: returned MLP · level recorded 2026-09-22
ManoLoss main/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1e910a336877a140 · report fixture: returned ManoLoss · level recorded 2026-09-22
ManoShapeLoss main/model.py ran no licence file found · pointer only · b6ab0eca0068eda3 · report fixture: signature pred_shape:Tensor/2/float, gt_shape:Tensor/1/float · returned tuple · level recorded 2026-09-24
SepSDFLoss main/model.py ran fingerprinted no licence file found · pointer only · 6886abcc87940b67 · report fixture: signature hand_sdf:Tensor/2/float, obj_sdf:Tensor/2/float, hand_sdf_gt:Tensor/1/float, obj_sdf_gt:Tensor/1/float · returned tuple · level recorded 2026-09-24
batch_rodrigues in 15 papers main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9af7256a400c370c · report fixture: signature theta:Tensor/2/float · returned Tensor · level recorded 2026-09-22
compute_ADD_s_error common/metrics.py ran no licence file found · pointer only · 233e7993d1c72c6a · report fixture: signature pred_pose:ndarray/2/float, gt_pose:ndarray/2/float, obj_mesh:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_nerf_embedder main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 31bcf9248a53c302 · report fixture: signature multires:int/0/int · returned tuple · level recorded 2026-09-22
make_conv_layers in 14 papers common/nets/layer.py ran no licence file found · pointer only · 622140af456ff5d2 · report fixture: signature feat_dims:list/1/int, kernel:int/0/int, stride:int/0/int, padding:int/0/int, bnrelu_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
make_deconv_layers in 5 papers common/nets/layer.py ran no licence file found · pointer only · 3a26e5305cd9fa2b · report fixture: signature feat_dims:list/1/int, bnrelu_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
make_linear_layers in 16 papers common/nets/layer.py ran · our draft was wrong no licence file found · pointer only · d47252198e2bc509 · report fixture: signature feat_dims:list/1/int, relu_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
mat2aa main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0cc7bfba9ee705d5 · report fixture: signature rotation_matrix:Tensor/3/float · returned Tensor · level recorded 2026-09-22
mat2quat main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5a85260f66f7f7c6 · report fixture: signature rotation_matrix:Tensor/3/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
quat2aa main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 40dc9f5943418548 · report fixture: signature quaternion:Tensor/2/float · returned Tensor · level recorded 2026-09-22
quat2mat in 26 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 918a33896f8c5b03 · report fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
rot6d2mat main/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4577e1a8ea4f6918 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
JointvoteLoss main/model.py unverified no licence file found · pointer only · 89460380e3ae666e · report
ManoHead main/model.py unverified no licence file found · pointer only · 2db0f55743d0b857 · report
Model in 227 papers main/model.py unverified no licence file found · pointer only · 749e3728103f0cd4 · report
build_transformer in 62 papers common/nets/transformer.py unverified no licence file found · pointer only · 47b8b020f555d270 · report
compute_obj_metrics_dexycb common/metrics.py unverified no licence file found · pointer only · d24f4bcc4407cecd · report
eval_batch_obj_direct common/metrics.py unverified no licence file found · pointer only · 221dcfbf7c552642 · report
make_folder main/model.py unverified no licence file found · pointer only · fc5e880b9424c83f · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for HOISDF (graph method: HOISDF). 17 bricks; individually on a fixture: 13 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Model entry · level 0 · unverified · 749e3728103f0cd4
  2. JointHeatmapLoss loss · level 1 · ran · 57de234ead12cd0d
  3. JointvoteLoss loss · level 0 · unverified · 89460380e3ae666e
  4. MLP helper · level 1 · ran · 15aa4edbfab28f4d
  5. ManoHead helper · level 0 · unverified · 2db0f55743d0b857
  6. ManoLoss loss · level 1 · ran · 1e910a336877a140
  7. ManoShapeLoss loss · level 1 · ran · b6ab0eca0068eda3
  8. SepSDFLoss loss · level 1 · ran · 6886abcc87940b67
  9. get_nerf_embedder helper · level 1 · ran · our draft was wrong · 31bcf9248a53c302
  10. batch_rodrigues helper · level 1 · ran · our draft was wrong · 9af7256a400c370c
  11. mat2aa helper · level 1 · ran · our draft was wrong · 0cc7bfba9ee705d5
  12. rot6d2mat helper · level 1 · ran · our draft was wrong · 4577e1a8ea4f6918
  13. Embedder helper · level 1 · ran · e61cc7bddc7d86e5
  14. quat2mat helper · level 1 · ran · our draft was wrong · 918a33896f8c5b03
  15. mat2quat helper · level 1 · ran · our draft was wrong · 5a85260f66f7f7c6
  16. quat2aa helper · level 1 · ran · our draft was wrong · 40dc9f5943418548
  17. make_folder helper · level 0 · unverified · fc5e880b9424c83f

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="2402.17062") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Hand Pose EstimationObjectPose Estimationhand-object pose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB HOISDF Average MPJPE (mm) 10.1 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HOISDF MPVPE 9.9 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HOISDF PA-MPVPE 4.9 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HOISDF PA-VAUC 90.2 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HOISDF Procrustes-Aligned MPJPE 5.13 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB HOISDF VAUC 80.5 #1 of 11 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 HOISDF PA-MPJPE (mm) 9.2 #12 of 24 Archive leaderboard report
hand-object pose DexYCB HOISDF ADD-S 13.3 #1 of 9 Archive leaderboard report
hand-object pose DexYCB HOISDF Average MPJPE (mm) 10.1 #1 of 9 Archive leaderboard report
hand-object pose DexYCB HOISDF MCE 27.4 #1 of 9 Archive leaderboard report
hand-object pose DexYCB HOISDF OCE 18.4 #1 of 9 Archive leaderboard report
hand-object pose DexYCB HOISDF Procrustes-Aligned MPJPE 5.31 #1 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HOISDF ADD-S 14.4 #1 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HOISDF Average MPJPE (mm) 19.0 #1 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HOISDF OME 35.5 #1 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HOISDF PA-MPJPE 9.2 #1 of 9 Archive leaderboard report
hand-object pose HO-3D v2 HOISDF ST-MPJPE 18.3 #1 of 9 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.

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