Neural Information Processing Systems http://nips.cc/

Accurate three-dimensional perception is essential for modern industrial robotic systems that perform manipulation, inspection, and navigation tasks. RGB-D and stereo vision sensors are widely used for this purpose, but the depth maps they produce are often noisy, incomplete, or biased due to sensor limitations and environmental conditions. Depth completion methods aim to generate dense, reliable depth maps from RGB images and sparse depth input. However, a key limitation in current depth completion pipelines is the unrealistic generation of sparse depth: sparse pixels are typically selected uniformly at random from dense ground-truth depth, ignoring the fact that real sensors exhibit geometry-dependent and spatially nonuniform reliability. In this work, we propose a normal-guided sparse depth sampling strategy that leverages PCA-based surface normal estimation on the RGB-D point cloud to compute a per-pixel depth reliability measure. The sparse depth samples are then drawn according to this reliability distribution. We integrate this sampling method with the Marigold-DC diffusion-based depth completion model and evaluate it on NYU Depth v2 using the standard metrics. Experiments show that our geometry-aware sparse depth improves accuracy, reduces artifacts near edges and discontinuities, and produces more realistic training conditions that better reflect real sensor behavior.

Abstract--The raw depth images captured by RGB-D cameras using Time-of-Flight (TOF) or structured light often suffer from incomplete depth values due to weak reflections, boundary shadows, and artifacts, which limit their applications in downstream vision tasks. Existing methods address this problem through depth completion in the image domain, but they overlook the physical characteristics of raw depth images. It has been observed that the presence of invalid depth areas alters the frequency distribution pattern. In this work, we propose a Spatio-Spectral Mutual Learning framework (S2ML) to harmonize the advantages of both spatial and frequency domains for depth completion. Specifically, we consider the distinct properties of amplitude and phase spectra and devise a dedicated spectral fusion module. Meanwhile, the local and global correlations between spatial-domain and frequency-domain features are calculated in a unified embedding space. The gradual mutual representation and refinement encourage the network to fully explore complementary physical characteristics and priors for more accurate depth completion. Extensive experiments demonstrate the effectiveness of our proposed S2ML method, outperforming the state-of-the-art method CFormer by 0.828 dB and 0.834 dB on the NYU-Depth V2 and SUN RGB-D datasets, respectively. EPTH sensing is essential for various 3D tasks such as autonomous driving [1], robot navigation [2], [3], and scene reconstruction [4], [5]. However, raw depth images captured by current depth sensors, such as Time-of-Flight (TOF) and structured light devices like Microsoft Kinect [6] and Intel Realsense [7], often contain significant invalid areas. These regions arise from factors such as highly reflective or transparent surfaces and challenging lighting conditions. Zhang, Y ang Li and Z. Geng are with the Institute of Data and Information, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China, 518071 (emails: zzh23@mails.tsinghua.edu.cn, Z. Wang is with School of Computer Science, Wuhan University, 430072, China (email: wangzwhu@whu.edu.cn). K. Jiang is with School of Computer Science and Technology, Harbin Institute of Technology, 150001, China (email: kuijiang 1994@163.com).

Depth perception of transparent and reflective objects has long been a critical challenge in robotic manipulation.Conventional depth sensors often fail to provide reliable measurements on such surfaces, limiting the performance of robots in perception and grasping tasks. To address this issue, we propose a novel depth completion network,HDCNet,which integrates the complementary strengths of Transformer,CNN and Mamba architectures.Specifically,the encoder is designed as a dual-branch Transformer-CNN framework to extract modality-specific features. At the shallow layers of the encoder, we introduce a lightweight multimodal fusion module to effectively integrate low-level features. At the network bottleneck,a Transformer-Mamba hybrid fusion module is developed to achieve deep integration of high-level semantic and global contextual information, significantly enhancing depth completion accuracy and robustness. Extensive evaluations on multiple public datasets demonstrate that HDCNet achieves state-of-the-art(SOTA) performance in depth completion tasks.Furthermore,robotic grasping experiments show that HDCNet substantially improves grasp success rates for transparent and reflective objects,achieving up to a 60% increase.

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured in novel environmental conditions due to a covariate shift. The crux of our method lies in quantifying the likelihood of depth predictions belonging to the source data distribution. The challenge is in the lack of access to out-of-distribution (target) data prior to deployment. Hence, rather than making assumptions regarding the target distribution, we utilize adversarial perturbations as a mechanism to explore the data space. This enables us to train an energy model that scores local regions of depth predictions as in- or out-of-distribution. We update the parameters of pretrained depth completion models at test time to minimize energy, effectively aligning test-time predictions to those of the source distribution. We call our method ``Energy-based Test-time Adaptation'', or ETA for short. We evaluate our method across three indoor and three outdoor datasets, where ETA improve over the previous state-of-the-art method by an average of 6.94% for outdoors and 10.23% for indoors. Project Page: https://fuzzythecat.github.io/eta.

CFCNet learns to capture, to the largest extent, the semantically correlated features between RGB and depth information.

-- Conventionally, human intuition often defines vision as a modality of passive optical sensing, while active optical sensing is typically regarded as measuring rather than the default modality of vision. However, the situation now changes: sensor technologies and data-driven paradigms empower active optical sensing to redefine the boundaries of vision, ushering in a new era of active vision . Light Detection and Ranging (LiDAR) sensors capture reflectance from object surfaces, which remains invariant under varying illumination conditions, showcasing significant potential in robotic perception tasks such as detection, recognition, segmentation, and Simultaneous Localization and Mapping (SLAM). These applications often rely on dense sensing capabilities, typically achieved by high-resolution, expensive LiDAR sensors. A key challenge with low-cost LiDARs lies in the sparsity of scan data, which limits their broader application. T o address this limitation, this work introduces an innovative framework for generating dense LiDAR reflectance images from sparse data, leveraging the unique attributes of non-repeating scanning LiDAR (NRS-LiDAR). We tackle critical challenges, including reflectance calibration and the transition from static to dynamic scene domains, facilitating the reconstruction of dense reflectance images in real-world settings. The key contributions of this work include a comprehensive dataset for LiDAR reflectance image densification, a densification network tailored for NRS-LiDAR, and diverse applications such as loop closure and traffic lane detection using the generated dense reflectance images. Experimental results validate the efficacy of the proposed approach, which successfully integrates computer vision techniques with LiDAR data processing, enhancing the applicability of low-cost LiDAR systems and establishing a novel paradigm for robotic active vision-- LiDAR as a Camera . The dataset and code are available at: T o Be Updated.

Depth information which specifies the distance between objects and current position of the robot is essential for many robot tasks such as navigation. Recently, researchers have proposed depth completion frameworks to provide dense depth maps that offer comprehensive information about the surrounding environment. However, existing methods show significant trade-offs between computational efficiency and accuracy during inference. The substantial memory and computational requirements make them unsuitable for real-time applications, highlighting the need to improve the completeness and accuracy of depth information while improving processing speed to enhance robot performance in various tasks. To address these challenges, in this paper, we propose CHADET(cross-hierarchical-attention depth-completion transformer), a lightweight depth-completion network that can generate accurate dense depth maps from RGB images and sparse depth points. For each pair, its feature is extracted from the depthwise blocks and passed to the equally lightweight transformer-based decoder. In the decoder, we utilize the novel cross-hierarchical-attention module that refines the image features from the depth information. Our approach improves the quality and reduces memory usage of the depth map prediction, as validated in both KITTI, NYUv2, and VOID datasets.