SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference

• URL: http://arxiv.org/abs/2509.21927v1
• Date: Fri, 26 Sep 2025 06:14:41 GMT
• Title: SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference
• Authors: Jiahui Wang, Haiyue Zhu, Haoren Guo, Abdullah Al Mamun, Cheng Xiang, Tong Heng Lee,
• Abstract summary: We propose SingRef6D, a lightweight pipeline requiring only a single RGB image as a reference.<n>First, we propose a token-scaler-based fine-tuning mechanism with a novel optimization loss on top of Depth-Anything v2 to enhance its ability to predict accurate depth.<n>Second, benefiting from depth availability, we introduce a depth-aware matching process, enabling our system to handle matching for challenging materials and lighting conditions.
• Score: 20.869522557117662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent 6D pose estimation methods demonstrate notable performance but still face some practical limitations. For instance, many of them rely heavily on sensor depth, which may fail with challenging surface conditions, such as transparent or highly reflective materials. In the meantime, RGB-based solutions provide less robust matching performance in low-light and texture-less scenes due to the lack of geometry information. Motivated by these, we propose SingRef6D, a lightweight pipeline requiring only a single RGB image as a reference, eliminating the need for costly depth sensors, multi-view image acquisition, or training view synthesis models and neural fields. This enables SingRef6D to remain robust and capable even under resource-limited settings where depth or dense templates are unavailable. Our framework incorporates two key innovations. First, we propose a token-scaler-based fine-tuning mechanism with a novel optimization loss on top of Depth-Anything v2 to enhance its ability to predict accurate depth, even for challenging surfaces. Our results show a 14.41% improvement (in $\delta_{1.05}$) on REAL275 depth prediction compared to Depth-Anything v2 (with fine-tuned head). Second, benefiting from depth availability, we introduce a depth-aware matching process that effectively integrates spatial relationships within LoFTR, enabling our system to handle matching for challenging materials and lighting conditions. Evaluations of pose estimation on the REAL275, ClearPose, and Toyota-Light datasets show that our approach surpasses state-of-the-art methods, achieving a 6.1% improvement in average recall.

Related papers

• UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing [77.10640210751981]
  UDPNet is a general framework that leverages depth-based priors from a large-scale pretrained depth estimation model DepthAnything V2.<n>Our proposed solution establishes a new benchmark for depth-aware dehazing across various scenarios.
  arXiv  Detail & Related papers  (2026-01-11T13:29:02Z)
• SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting [3.6688867031495223]
  We introduce SplatPose, a novel framework that synergizes 3D Gaussian Splatting (3DGS) with a dual-branch neural architecture to achieve high-precision pose estimation.<n> Experiments on three benchmark datasets demonstrate that SplatPose achieves state-of-the-art 6-DoF pose estimation accuracy in single RGB settings.
  arXiv  Detail & Related papers  (2025-03-07T06:40:06Z)
• Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior [3.2120448116996103]
  This paper proposes the first self-supervision for deep-learning depth estimation on water scenes via intra-frame priors. In the first stage, a water segmentation network is performed to separate the reflection components from the entire image. The photometric re-projection error, incorporating SmoothL1 and a novel photometric adaptive SSIM, is formulated to optimize pose and depth estimation.
  arXiv  Detail & Related papers  (2024-04-10T17:25:42Z)
• Confidence-Aware RGB-D Face Recognition via Virtual Depth Synthesis [48.59382455101753]
  2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. In this work, we first construct a diverse depth dataset generated by 3D Morphable Models for depth model pre-training. Then, we propose a domain-independent pre-training framework that utilizes readily available pre-trained RGB and depth models to separately perform face recognition without needing additional paired data for retraining.
  arXiv  Detail & Related papers  (2024-03-11T09:12:24Z)
• Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution [52.582632746409665]
  We propose a novel Symmetric Uncertainty-aware Feature Transmission (SUFT) for color-guided DSR. Our method achieves superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-01T06:35:59Z)
• DARF: Depth-Aware Generalizable Neural Radiance Field [51.29437249009986]
  We propose the Depth-Aware Generalizable Neural Radiance Field (DARF) with a Depth-Aware Dynamic Sampling (DADS) strategy.<n>Our framework infers the unseen scenes on both pixel level and geometry level with only a few input images.<n>Compared with state-of-the-art generalizable NeRF methods, DARF reduces samples by 50%, while improving rendering quality and depth estimation.
  arXiv  Detail & Related papers  (2022-12-05T14:00:59Z)
• MonoGraspNet: 6-DoF Grasping with a Single RGB Image [73.96707595661867]
  6-DoF robotic grasping is a long-lasting but unsolved problem. Recent methods utilize strong 3D networks to extract geometric grasping representations from depth sensors. We propose the first RGB-only 6-DoF grasping pipeline called MonoGraspNet.
  arXiv  Detail & Related papers  (2022-09-26T21:29:50Z)
• 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)
• Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs [1.0499611180329802]
  Real-time estimation of actual environment depth is an essential module for various autonomous system tasks. In this study, latest advancements in the field of generative neural networks are leveraged to fully unsupervised single-image depth synthesis.
  arXiv  Detail & Related papers  (2021-03-31T09:43:38Z)

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.