Papers › A Visual Navigation Perspective for Category-Level Object Pose Estimation

A Visual Navigation Perspective for Category-Level Object Pose Estimation

25 Mar 2022arXiv:2203.13572archive 2025-07-28

Jiaxin Guo, Fangxun Zhong, Rong Xiong, Yunhui Liu, Yue Wang, Yiyi Liao

This paper studies category-level object pose estimation based on a single monocular image. Recent advances in pose-aware generative models have paved the way for addressing this challenging task using analysis-by-synthesis. The idea is to sequentially update a set of latent variables, e.g., pose, shape, and appearance, of the generative model until the generated image best agrees with the observation. However, convergence and efficiency are two challenges of this inference procedure. In this paper, we take a deeper look at the inference of analysis-by-synthesis from the perspective of visual navigation, and investigate what is a good navigation policy for this specific task. We evaluate three different strategies, including gradient descent, reinforcement learning and imitation learning, via thorough comparisons in terms of convergence, robustness and efficiency. Moreover, we show that a simple hybrid approach leads to an effective and efficient solution. We further compare these strategies to state-of-the-art methods, and demonstrate superior performance on synthetic and real-world datasets leveraging off-the-shelf pose-aware generative models.

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="2203.13572")

Code

Syntology Ran 2 of 17 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: official repository: 17 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wrld/visual_navigation_pose_estimation officialmentioned in papermentioned on GitHubpytorchMIT 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

17 samples harvested; 2 ran; 2 honoured the contract we drafted; 15 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.

2ran · honoured contract
15unverified

Licence: 0 of the 17 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 wrld/visual_navigation_pose_estimation. “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.

create_window wrld/visual_navigation_pose_estimation/models/networks/losses.py official repository ran · honoured contract fingerprinted MIT (permissive) · 6154e3744ece5728 · report
gaussian wrld/visual_navigation_pose_estimation/models/networks/losses.py official repository ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report
actvn wrld/visual_navigation_pose_estimation/models/networks/networks.py official repository unverified MIT (permissive) · 5bd96fb5938773d4 · report
compute_RotMats wrld/visual_navigation_pose_estimation/utils/loss.py official repository unverified MIT (permissive) · 5be53270342b91a6 · report
compute_iou wrld/visual_navigation_pose_estimation/nocs/utils.py official repository unverified MIT (permissive) · 2757c39fd1d64ab6 · report
compute_overlaps wrld/visual_navigation_pose_estimation/nocs/utils.py official repository unverified MIT (permissive) · d8f86755404a2057 · report
euler2mat wrld/visual_navigation_pose_estimation/models/networks/networks.py official repository unverified MIT (permissive) · 966e21cead161e27 · report
extract_bboxes wrld/visual_navigation_pose_estimation/nocs/utils.py official repository unverified MIT (permissive) · 75499b9fb42b31f7 · report
grid_sample wrld/visual_navigation_pose_estimation/models/networks/utils.py official repository unverified MIT (permissive) · 774db7133dd29213 · report
init_variable wrld/visual_navigation_pose_estimation/models/networks/utils.py official repository unverified MIT (permissive) · 3980d98cced8b905 · report
remove_spectral_norm wrld/visual_navigation_pose_estimation/models/networks/spectral_norm.py official repository unverified MIT (permissive) · a9881435918e1dc4 · report
rot wrld/visual_navigation_pose_estimation/models/networks/networks.py official repository unverified MIT (permissive) · 01df6fccefdc574e · report
rot_error wrld/visual_navigation_pose_estimation/utils/loss.py official repository unverified MIT (permissive) · 65e457d25bcad96a · report
spectral_norm wrld/visual_navigation_pose_estimation/models/networks/spectral_norm.py official repository unverified MIT (permissive) · 9cf6a2515e727176 · report
ssim wrld/visual_navigation_pose_estimation/models/networks/losses.py official repository unverified MIT (permissive) · b21bebe6240b182c · report
trans_error wrld/visual_navigation_pose_estimation/utils/loss.py official repository unverified MIT (permissive) · af3c4a71bdfa4413 · report
warping_grid wrld/visual_navigation_pose_estimation/models/networks/utils.py official repository unverified MIT (permissive) · bec655e3507fba1e · report

Tasks

Imitation LearningPose EstimationVisual Navigation

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