SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.07419 · ICML · 2026

DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation

Tolga Birdal, Nassir Navab, Tony Wang, Lennart Bastian

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
wngTn/DisPOSE — 1 of 3
FunctionStatusWhere it lives
_extract_1d Ran wngTn/DisPOSE/src/models/assignment/sampler.py
code served (permissive licence) · get_code("840e5c9d37be6a6b")
ProjectedConstrainedDDIM Not yet run wngTn/DisPOSE/src/models/assignment/sampler.py
code served (permissive licence) · get_code("7461abad4c33f1fa")
_cosine_alpha_bar Not yet run wngTn/DisPOSE/src/models/assignment/sampler.py
code served (permissive licence) · get_code("1eb4d1aeeeb8a945")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. We present DISPOSE, a novel pose estimation framework that models the discrete problem of associating individuals from multiple camera views as a generative process. By diffusing over the space of polystochastic tensors, DISPOSE learns to recover accurate 3D human associations without requiring 3D ground-truth supervision. As visualized in the trajectory (left to right), the diffusion process progressively resolves ambiguity, evolving from noise into sharp, consistent multi-view associations.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.07419")
get_code_for_paper("2606.07419")
have("2606.07419")

Connect an agent — have() is free.