Papers › Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

25 Mar 2024arXiv:2403.16428archive 2025-07-28

Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Zheng Liu, Feng Lu, Karim Abou Zeid, Bastian Leibe, Jeongwan On, Seungryul Baek, Aditya Prakash, Saurabh Gupta, Kun He, Yoichi Sato, Otmar Hilliges, Hyung Jin Chang, Angela Yao

We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in 3D is challenging due to heavy occlusion, viewpoint bias, camera distortion, and motion blur from the head movement. To this end, we designed the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks. Our analysis demonstrates the effectiveness of addressing distortion specific to egocentric cameras, adopting high-capacity transformers to learn complex hand-object interactions, and fusing predictions from different views. Our study further reveals challenging scenarios intractable with state-of-the-art methods, such as fast hand motion, object reconstruction from narrow egocentric views, and close contact between two hands and objects. Our efforts will enrich the community's knowledge foundation and facilitate future hand studies on egocentric hand-object interactions.

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 14 code samples harvested from 2 repositories linked to this paper: 11 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; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 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: 6 samples from 1 repository, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 5 ran (4 with no instrument failure; 1 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.

facebookresearch/assemblyhands-toolkit officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
zc-alexfan/arctic mentioned on GitHubpytorchNOASSERTIONSyntology: 8 samples, 5 ran (1 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

14 samples harvested: 11 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; 5 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.

3ran · our draft was wrong
2ran; the contract check could not run
6ran
3unverified

Licence: 14 of the 14 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 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.

facebookresearch/assemblyhands-toolkit official repository 6 samples, 6 ran (4 instrument-failed) · 0 unverified
as_4x4 calib/affine.py ran · our draft was wrong licence not identified · pointer only · cf75fc1410290cdd · report fixture: signature a:ndarray/2/float, copy:bool/0/bool · returned ndarray · level recorded 2026-09-24
make_conv_layers in 14 papers src/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 src/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 src/common/nets/layer.py ran · our draft was wrong licence not identified · pointer only · d47252198e2bc509 · report fixture: signature feat_dims:list/1/int, relu_final:bool/0/bool · returned Sequential · level recorded 2026-09-24
transform3 calib/affine.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 90aee4c3a531dd4a · report fixture: signature m:ndarray/2/float, v:ndarray/2/float · returned ndarray · level recorded 2026-09-24
transform_vec3 calib/affine.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 9651c3a7006b8b88 · report fixture: signature m:ndarray/2/float, v:ndarray/2/float · returned ndarray · level recorded 2026-09-24
zc-alexfan/arctic community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
compute_bbox_batch src/arctic/processing.py ran fingerprinted licence not identified · pointer only · 0772ce944023d5d6 · report fixture: signature kp2d:Tensor/3/float, obj_s:float/0/float · returned tuple · level recorded 2026-09-24
construct_hand_meshes src/mesh_loaders/arctic.py ran licence not identified · pointer only · 016960858e5e23d2 · report fixture: signature cam_data:dict/0/?, layers:dict/0/?, view_idx:int/0/int, distort:bool/0/bool · returned tuple · level recorded 2026-09-24
get_selected_seqs src/arctic/split.py ran · our draft was wrong licence not identified · pointer only · 86609ce52e4a5bde · report fixture: signature setup:str/0/str, split:str/0/str · returned list · level recorded 2026-09-24
get_selected_views src/arctic/split.py ran licence not identified · pointer only · 86a8c70534f5aa9b · report fixture: signature setup:str/0/str, split:str/0/str · returned list · level recorded 2026-09-24
glob_fnames src/arctic/split.py ran licence not identified · pointer only · dfdfc61e8a39ff0b · report fixture: signature num_frames:int/0/int, seq:str/0/str, chosen_views:list/1/str · returned list · level recorded 2026-09-24
construct_loader in 6 papers src/arctic/preprocess_dataset.py unverified licence not identified · pointer only · 2a5971e23c58e3cb · report
construct_smplx_meshes src/mesh_loaders/arctic.py unverified licence not identified · pointer only · 525b32ea87401255 · report
forward_define_bbox src/arctic/processing.py unverified licence not identified · pointer only · 98e114e6083a05c8 · report

Tasks

Action RecognitionMotion GenerationObjectObject ReconstructionPose Estimation

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