Papers › ODIN: A Single Model for 2D and 3D Segmentation

ODIN: A Single Model for 2D and 3D Segmentation

4 Jan 2024CVPR 2024 1arXiv:2401.02416archive 2025-07-28

Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).

PaperPDFConference PDFCodeCode 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="2401.02416")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 8 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.

ayushjain1144/odin officialpytorchMIT 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

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 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
5unverified

Licence: 0 of the 8 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 ayushjain1144/odin. “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.

collate_fn ayushjain1144/odin/odin/data_video/build.py official repository ran MIT (permissive) · 477e6413e38c667b · report
custom_image_augmentations ayushjain1144/odin/odin/data_video/dataset_mapper_scannet.py official repository ran MIT (permissive) · a26f0c5d307ec0ab · report
intersection_and_union_gpu ayushjain1144/odin/odin/data_video/scannet_3d_eval_semantic.py official repository ran MIT (permissive) · 7d7d9cdce5fee3dc · report
batch_dice_loss ayushjain1144/odin/odin/modeling/matcher.py official repository unverified MIT (permissive) · bc2cb481a75c370d · report
batch_sigmoid_ce_loss ayushjain1144/odin/odin/modeling/matcher.py official repository unverified MIT (permissive) · 1edd24985036b0bf · report
calculate_uncertainty ayushjain1144/odin/odin/modeling/criterion.py official repository unverified MIT (permissive) · 2dcb8123d89bb1ff · report
dice_loss ayushjain1144/odin/odin/modeling/criterion.py official repository unverified MIT (permissive) · 89f75e54ff128be0 · report
sigmoid_ce_loss ayushjain1144/odin/odin/modeling/criterion.py official repository unverified MIT (permissive) · d0c61e8dba511aa3 · report

Tasks

3D Instance Segmentation3D Semantic SegmentationInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation ScanNet(v2) ODIN mAP 50.0 #14 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) ODIN mAP @ 50 71.0 #14 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) ODIN mAP@25 83.6 #14 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet200 ODIN mAP 31.5 #1 of 5 Archive leaderboard report
3D Instance Segmentation ScanNet200 ODIN mAP@25 53.1 #1 of 5 Archive leaderboard report
3D Instance Segmentation ScanNet200 ODIN mAP@50 45.3 #1 of 5 Archive leaderboard report
3D Semantic Segmentation ScanNet200 ODIN test mIoU 36.8 #2 of 16 Archive leaderboard report
3D Semantic Segmentation ScanNet200 ODIN val mIoU 40.5 #2 of 16 Archive leaderboard report
Semantic Segmentation ScanNet ODIN test mIoU 74.4 #6 of 45 Archive leaderboard report
Semantic Segmentation ScanNet ODIN val mIoU 77.8 #6 of 45 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