Papers › EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models

EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models

14 Jun 2024arXiv:2406.10224archive 2025-07-28

Julian Straub, Daniel DeTone, Tianwei Shen, Nan Yang, Chris Sweeney, Richard Newcombe

The advent of wearable computers enables a new source of context for AI that is embedded in egocentric sensor data. This new egocentric data comes equipped with fine-grained 3D location information and thus presents the opportunity for a novel class of spatial foundation models that are rooted in 3D space. To measure progress on what we term Egocentric Foundation Models (EFMs) we establish EFM3D, a benchmark with two core 3D egocentric perception tasks. EFM3D is the first benchmark for 3D object detection and surface regression on high quality annotated egocentric data of Project Aria. We propose Egocentric Voxel Lifting (EVL), a baseline for 3D EFMs. EVL leverages all available egocentric modalities and inherits foundational capabilities from 2D foundation models. This model, trained on a large simulated dataset, outperforms existing methods on the EFM3D benchmark.

PaperPDFCodeCode Syntology ran

In Syntology 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="2406.10224")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/efm3d officialmentioned 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

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran

Licence: 0 of the 3 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 facebookresearch/efm3d. “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.

add_residual facebookresearch/efm3d/efm3d/model/dinov2_utils.py official repository ran Apache-2.0 (permissive) · 3f66b5f677e07adc · report
drop_add_residual_stochastic_depth facebookresearch/efm3d/efm3d/model/dinov2_utils.py official repository ran Apache-2.0 (permissive) · 4d7d35dca4659acd · report
get_branges_scales facebookresearch/efm3d/efm3d/model/dinov2_utils.py official repository ran fingerprinted Apache-2.0 (permissive) · de16c8c98b583b6a · report

Tasks

3D Object Detection3D ReconstructionMulti-View 3D ReconstructionObject Detectionobject-detection

Datasets

Introduced by this paper, per the archive.

Aria Everyday Objects

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection Aria Everyday Objects EVL mAP 22 #1 of 4 Archive leaderboard report
3D Object Detection Aria Everyday Objects 3DETR mAP 16 #2 of 4 Archive leaderboard report
3D Object Detection Aria Everyday Objects ImVoxelNet mAP 15 #3 of 4 Archive leaderboard report
3D Object Detection Aria Everyday Objects Cube R-CNN mAP 8 #4 of 4 Archive leaderboard report
3D Object Detection Aria Synthetic Environments EVL MAP 75 #1 of 4 Archive leaderboard report
3D Object Detection Aria Synthetic Environments ImVoxelNet MAP 64 #2 of 4 Archive leaderboard report
3D Object Detection Aria Synthetic Environments Cube R-CNN MAP 36 #3 of 4 Archive leaderboard report
3D Object Detection Aria Synthetic Environments 3DETR MAP 33 #4 of 4 Archive leaderboard report
3D Reconstruction Aria Digital Twin Dataset EVL Accuracy 18.2 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Digital Twin Dataset EVL Completeness 3.105 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Digital Twin Dataset EVL Precision 59.4 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Synthetic Environments EVL Accuracy 5.7 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Synthetic Environments EVL Completeness 87.7 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Synthetic Environments EVL Precision 82.2 #1 of 1 Archive leaderboard report
3D Reconstruction Aria Synthetic Environments EVL Recall 10.6 #1 of 1 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