Foundational feature fusion for conditional flow matching in 6D pose estimation

• URL: http://arxiv.org/abs/2608.29183v1
• Date: Sat, 29 Aug 2026 10:20:17 GMT
• Title: Foundational feature fusion for conditional flow matching in 6D pose estimation
• Abstract summary: Conditional flow matching has enabled a step forward in object 6D pose estimation.<n>Existing methods require training task-specific encoders supervised on object-scene overlap.<n>We present FunFlow6D, a novel flow matching-based formulation.
• Score: 17.727631844746835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conditional flow matching has enabled a step forward in object 6D pose estimation, achieving state-of-the-art performance by progressively denoising and registering object representations to observed scenes. Existing methods require training task-specific encoders supervised on object-scene overlap and rely on trivial feature fusion strategies to resolve pose ambiguities. We present FunFlow6D, a novel flow matching-based formulation that leverages features from geometric and appearance foundation models for pose estimation, eliminating the need for task-specific encoder training. We also introduce a cross attention-based fusion mechanism that dynamically combines geometric and appearance features to provide richer conditioning for the flow matching module. Experiments on four datasets from the BOP benchmark show that FunFlow6D outperforms the previous state of the art while reducing supervision requirements and memory overhead. Extensive ablations validate the contribution of each proposed component. Project website: https://tev-fbk.github.io/FunFlow6D/.

Related papers

• Prior-free relative 6D pose estimation of multiple object instances [15.516176223256641]
  We introduce prior-free relative 6D pose estimation, which lifts the assumption of knowing which object is to be posed within the scene.<n>This novel setting aims to estimate the relative poses of multiple instances of an unknown object within the same image, without requiring CAD models, templates, or reference images.
  arXiv  Detail & Related papers  (2026-09-08T16:07:33Z)
• Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation [18.258165456031975]
  Flow6D is a hierarchical flow matching framework with a two-stage discrete latent space localization-continuous pose regression strategy.<n>The framework naturally extends to articulated objects, outperforming state-of-the-art methods on synthetic and real datasets with real-time inference at 70 FPS.
  arXiv  Detail & Related papers  (2026-06-22T13:05:55Z)
• GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry [61.24189040578178]
  We propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms.<n>Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion.<n>Our approach achieves state-of-the-art motion segmentation performance with high efficiency.
  arXiv  Detail & Related papers  (2026-02-25T11:36:33Z)
• Visual Autoregressive Modelling for Monocular Depth Estimation [69.01449528371916]
  We propose a monocular depth estimation method based on visual autoregressive ( VAR) priors.<n>Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism.<n>We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets.
  arXiv  Detail & Related papers  (2025-12-27T17:08:03Z)
• GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects [14.598853174946656]
  We present GenFlow, an approach that enables both accuracy and generalization to novel objects. Our method predicts optical flow between the rendered image and the observed image and refines the 6D pose iteratively. It boosts the performance by a constraint of the 3D shape and the generalizable geometric knowledge learned from an end-to-end differentiable system.
  arXiv  Detail & Related papers  (2024-03-18T06:32:23Z)
• Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation [7.064953237013352]
  We revisit Fully Convolutional Geometric Features (FCGF) and tailor it for object 6D pose estimation to achieve state-of-the-art performance. FCGF employs sparse convolutions and learns point-level features using a fully-convolutional network by optimising a hardest contrastive loss. We can outperform recent competitors on popular benchmarks by adopting key modifications to the loss and to the input data representations.
  arXiv  Detail & Related papers  (2023-07-28T12:16:31Z)
• Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features [17.920305227880245]
  We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of the neural feature activations at each mesh. Our experiments demonstrate an enhanced category-level 6D pose estimation performance compared to prior work.
  arXiv  Detail & Related papers  (2022-09-12T21:31:36Z)
• DeepRM: Deep Recurrent Matching for 6D Pose Refinement [77.34726150561087]
  DeepRM is a novel recurrent network architecture for 6D pose refinement. The architecture incorporates LSTM units to propagate information through each refinement step. DeepRM achieves state-of-the-art performance on two widely accepted challenging datasets.
  arXiv  Detail & Related papers  (2022-05-28T16:18:08Z)
• Semantic keypoint-based pose estimation from single RGB frames [64.80395521735463]
  We present an approach to estimating the continuous 6-DoF pose of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. We show that our approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios.
  arXiv  Detail & Related papers  (2022-04-12T15:03:51Z)
• FS6D: Few-Shot 6D Pose Estimation of Novel Objects [116.34922994123973]
  6D object pose estimation networks are limited in their capability to scale to large numbers of object instances. In this work, we study a new open set problem; the few-shot 6D object poses estimation: estimating the 6D pose of an unknown object by a few support views without extra training.
  arXiv  Detail & Related papers  (2022-03-28T10:31:29Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)
• Spatial Attention Improves Iterative 6D Object Pose Estimation [52.365075652976735]
  We propose a new method for 6D pose estimation refinement from RGB images. Our main insight is that after the initial pose estimate, it is important to pay attention to distinct spatial features of the object. We experimentally show that this approach learns to attend to salient spatial features and learns to ignore occluded parts of the object, leading to better pose estimation across datasets.
  arXiv  Detail & Related papers  (2021-01-05T17:18:52Z)
• A Pose Proposal and Refinement Network for Better Object Pose Estimation [0.5735035463793008]
  We present a novel, end-to-end 6D object pose estimation method that operates on RGB inputs. Our proposed pipeline outperforms state-of-the-art RGB-based methods with competitive runtime performance.
  arXiv  Detail & Related papers  (2020-04-11T23:13:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.