Papers › Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

23 Nov 2016CVPR 2017 7arXiv:1611.07828archive 2025-07-28

Georgios Pavlakos, Xiaowei Zhou, Konstantinos G. Derpanis, Kostas Daniilidis

This paper addresses the challenge of 3D human pose estimation from a single color image. Despite the general success of the end-to-end learning paradigm, top performing approaches employ a two-step solution consisting of a Convolutional Network (ConvNet) for 2D joint localization and a subsequent optimization step to recover 3D pose. In this paper, we identify the representation of 3D pose as a critical issue with current ConvNet approaches and make two important contributions towards validating the value of end-to-end learning for this task. First, we propose a fine discretization of the 3D space around the subject and train a ConvNet to predict per voxel likelihoods for each joint. This creates a natural representation for 3D pose and greatly improves performance over the direct regression of joint coordinates. Second, to further improve upon initial estimates, we employ a coarse-to-fine prediction scheme. This step addresses the large dimensionality increase and enables iterative refinement and repeated processing of the image features. The proposed approach outperforms all state-of-the-art methods on standard benchmarks achieving a relative error reduction greater than 30% on average. Additionally, we investigate using our volumetric representation in a related architecture which is suboptimal compared to our end-to-end approach, but is of practical interest, since it enables training when no image with corresponding 3D groundtruth is available, and allows us to present compelling results for in-the-wild images.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

geopavlakos/c2f-vol-demo mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
geopavlakos/c2f-vol-train mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
strawberryfg/c2f-3dhm-human-caffe mentioned on GitHubtorchSyntology: not harvested report
thuml/ContextWM mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning (arXiv:2305.18499; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation HumanEva-I c2f-vol Mean Reconstruction Error (mm) 24.3 #18 of 31 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