Selected work

Representative Papers

Pose Anything Anywhere:Model-free Object Poses from Arbitrary References

Jun 22, 2026

This work addresses the challenging problem of 6D object pose estimation for unseen objects in open-world scenarios, where severe occlusions, large viewpoint variations, and sparse or absent pose annotations in reference images are prevalent. To tackle this, the authors propose PANY, a unified model-free framework that operates with only one or a few pose-annotated reference images. PANY leverages a multi-view Transformer-based geometric backbone to learn view-consistent structures and cross-view alignment cues, and incorporates pose-graph regularized registration to fuse geometric information when auxiliary views are available. Breaking away from conventional pairwise matching paradigms, PANY supports arbitrary reference settings with either RGB or RGB-D inputs. Experiments demonstrate that PANY significantly outperforms existing model-free methods on the YCB-Video and LineMOD-Occlusion benchmarks, achieving pose accuracy improvements of 12% and over 20%, respectively, while exhibiting strong robustness in real-world scenes.

0 citationsRead paper

BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies

Oct 23, 2025

To address performance degradation in 2D detection of unseen objects under complex backgrounds, low illumination, and cluttered conditions in industrial settings, this paper proposes a standardized, plug-and-play robust detection pipeline. Methodologically, it integrates foundation model–guided open-vocabulary detection, SAM-based instance segmentation, adaptive background suppression, and low-light image enhancement into a synergistic optimization framework—effectively mitigating SAM false positives and alleviating domain shift. The pipeline requires no prior knowledge of target objects and enables zero-shot generalization. Evaluated on the BOP real-world industrial sorting benchmark, it achieves substantial gains in detection accuracy with minimal inference overhead, demonstrating both effectiveness and edge-deployment feasibility. The core contribution is the first lightweight, multi-stage robust detection paradigm specifically designed for unseen industrial objects, achieving balanced optimization of accuracy and efficiency.

0 citationsRead paper

RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation

Oct 21, 2025

To address accuracy degradation in template-based 6D pose estimation caused by template retrieval failure, this paper proposes a ray-alignment paradigm: modeling pose estimation as a geometric alignment task between the query image and multi-view template images in camera-ray space. Key contributions include: (1) reparameterizing camera rays with the object center as origin to decouple and explicitly model rotation; (2) jointly constraining translation estimation via dense translation offsets and geometric priors (e.g., depth consistency); and (3) designing a coarse-to-fine diffusion Transformer architecture that achieves scale-invariant rotation prediction and dense displacement regression through a ray-bundle diffusion mechanism. The method achieves state-of-the-art performance across multiple benchmarks and demonstrates superior robustness and generalization to unseen objects.

0 citationsRead paper

GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks

Oct 01, 2025

To address high spillage rates and low reliability in robotic food scooping—caused by the dynamic and heterogeneous physical states of food—this paper proposes a spillage-aware guided diffusion policy. Methodologically, we introduce diffusion models to this task for the first time, constructing a differentiable spillage predictor grounded in physics-based simulation; its gradient signal is leveraged to guide real-time generation of safe, low-spillage trajectories. Our technical contributions are: (1) a differentiable spillage modeling framework with gradient-based policy guidance, and (2) a simulation-to-real generalization training paradigm. Trained on six food categories, the method achieves 82% task success and only 4% spillage on ten unseen food categories—reducing spillage by over 40% compared to an unguided baseline. Results demonstrate substantial improvements in robustness and safety for cross-category food manipulation.

0 citationsRead paper

XYZ-IBD: High-precision Bin-picking Dataset for Object 6D Pose Estimation Capturing Real-world Industrial Complexity

May 31, 2025

Existing 6D pose datasets predominantly target domestic scenes and fail to capture realistic industrial bin-picking challenges—such as metallic reflectivity, severe occlusion, high-density clutter, and symmetric, textureless objects. To address this gap, we propose XYZ-IBD, the first high-fidelity, industrial-grade 6D pose benchmark explicitly designed for bin-picking. It comprises 75 multi-view real-world scenes and large-scale photorealistic synthetic data. Our method systematically models industrial complexity via anti-reflective surface coating, multi-view RGB-D fusion, Sim2Real rendering, and a semi-automatic annotation pipeline—achieving sub-millimeter ground-truth accuracy. Benchmarking reveals substantial performance degradation of current state-of-the-art methods on XYZ-IBD, underscoring its rigor and realism. We publicly release the dataset, annotation tools, and a comprehensive evaluation protocol to advance robust, deployable 6D perception research for industrial automation.

0 citationsRead paper

Recent publications

Latest Papers

Pose Anything Anywhere:Model-free Object Poses from Arbitrary References

Jun 22, 2026

This work addresses the challenging problem of 6D object pose estimation for unseen objects in open-world scenarios, where severe occlusions, large viewpoint variations, and sparse or absent pose annotations in reference images are prevalent. To tackle this, the authors propose PANY, a unified model-free framework that operates with only one or a few pose-annotated reference images. PANY leverages a multi-view Transformer-based geometric backbone to learn view-consistent structures and cross-view alignment cues, and incorporates pose-graph regularized registration to fuse geometric information when auxiliary views are available. Breaking away from conventional pairwise matching paradigms, PANY supports arbitrary reference settings with either RGB or RGB-D inputs. Experiments demonstrate that PANY significantly outperforms existing model-free methods on the YCB-Video and LineMOD-Occlusion benchmarks, achieving pose accuracy improvements of 12% and over 20%, respectively, while exhibiting strong robustness in real-world scenes.

0 citationsRead paper

BioDet: Boosting Industrial Object Detection with Image Preprocessing Strategies

Oct 23, 2025

To address performance degradation in 2D detection of unseen objects under complex backgrounds, low illumination, and cluttered conditions in industrial settings, this paper proposes a standardized, plug-and-play robust detection pipeline. Methodologically, it integrates foundation model–guided open-vocabulary detection, SAM-based instance segmentation, adaptive background suppression, and low-light image enhancement into a synergistic optimization framework—effectively mitigating SAM false positives and alleviating domain shift. The pipeline requires no prior knowledge of target objects and enables zero-shot generalization. Evaluated on the BOP real-world industrial sorting benchmark, it achieves substantial gains in detection accuracy with minimal inference overhead, demonstrating both effectiveness and edge-deployment feasibility. The core contribution is the first lightweight, multi-stage robust detection paradigm specifically designed for unseen industrial objects, achieving balanced optimization of accuracy and efficiency.

0 citationsRead paper

RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation

Oct 21, 2025

To address accuracy degradation in template-based 6D pose estimation caused by template retrieval failure, this paper proposes a ray-alignment paradigm: modeling pose estimation as a geometric alignment task between the query image and multi-view template images in camera-ray space. Key contributions include: (1) reparameterizing camera rays with the object center as origin to decouple and explicitly model rotation; (2) jointly constraining translation estimation via dense translation offsets and geometric priors (e.g., depth consistency); and (3) designing a coarse-to-fine diffusion Transformer architecture that achieves scale-invariant rotation prediction and dense displacement regression through a ray-bundle diffusion mechanism. The method achieves state-of-the-art performance across multiple benchmarks and demonstrates superior robustness and generalization to unseen objects.

0 citationsRead paper

GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks

Oct 01, 2025

To address high spillage rates and low reliability in robotic food scooping—caused by the dynamic and heterogeneous physical states of food—this paper proposes a spillage-aware guided diffusion policy. Methodologically, we introduce diffusion models to this task for the first time, constructing a differentiable spillage predictor grounded in physics-based simulation; its gradient signal is leveraged to guide real-time generation of safe, low-spillage trajectories. Our technical contributions are: (1) a differentiable spillage modeling framework with gradient-based policy guidance, and (2) a simulation-to-real generalization training paradigm. Trained on six food categories, the method achieves 82% task success and only 4% spillage on ten unseen food categories—reducing spillage by over 40% compared to an unguided baseline. Results demonstrate substantial improvements in robustness and safety for cross-category food manipulation.

0 citationsRead paper

XYZ-IBD: High-precision Bin-picking Dataset for Object 6D Pose Estimation Capturing Real-world Industrial Complexity

May 31, 2025

Existing 6D pose datasets predominantly target domestic scenes and fail to capture realistic industrial bin-picking challenges—such as metallic reflectivity, severe occlusion, high-density clutter, and symmetric, textureless objects. To address this gap, we propose XYZ-IBD, the first high-fidelity, industrial-grade 6D pose benchmark explicitly designed for bin-picking. It comprises 75 multi-view real-world scenes and large-scale photorealistic synthetic data. Our method systematically models industrial complexity via anti-reflective surface coating, multi-view RGB-D fusion, Sim2Real rendering, and a semi-automatic annotation pipeline—achieving sub-millimeter ground-truth accuracy. Benchmarking reveals substantial performance degradation of current state-of-the-art methods on XYZ-IBD, underscoring its rigor and realism. We publicly release the dataset, annotation tools, and a comprehensive evaluation protocol to advance robust, deployable 6D perception research for industrial automation.

0 citationsRead paper