Core Viewpoint - The article discusses the limitations of existing depth estimation and completion models due to reliance on outdated datasets, highlighting the significance of the newly released LingBot-Depth-Dataset by Ant Group, which provides a large-scale, high-quality RGB-depth dataset to enhance model training and performance in real-world applications [4][5][34]. Group 1: Dataset Overview - Ant Group has open-sourced approximately 3 million pairs of high-quality RGB-depth data, making it one of the largest real-world RGB-D datasets available [5][16]. - The dataset consists of 2.71TB of data, including around 2 million pairs of real RGB-D data and 1 million pairs of high-quality rendered data, covering six mainstream depth cameras [5][6]. - The dataset is structured into four subsets: RobbyReal, RobbyVla, RobbySim, and RobbySimVal, each designed to address specific challenges in depth perception tasks [17][22][24]. Group 2: Importance of Real Data - The article emphasizes the challenges in obtaining high-quality real RGB-D data, including high costs, technical complexities, and the inherent limitations of depth sensors [12][13][14]. - The lack of large-scale real-world RGB-D datasets has created a gap in the field, which the LingBot-Depth-Dataset aims to fill, providing a critical resource for advancing depth estimation technologies [14][34]. - The dataset's design allows models to learn from diverse sensor characteristics, improving their generalization across different hardware environments [19][20]. Group 3: Impact on the Industry - The introduction of the LingBot-Depth-Dataset is expected to shift the focus from model complexity to data quality, as the performance of models is increasingly determined by the quality and quantity of training data [31][32]. - This dataset could serve as a new benchmark for depth estimation and completion, similar to how ImageNet transformed visual recognition [34][35]. - By providing a comprehensive dataset, Ant Group enables research teams to concentrate on higher-level problems without the need to collect data from scratch, fostering innovation in the field [36].

Core Viewpoint - The article discusses the InfiniDepth method, which utilizes a novel continuous approach to achieve significantly improved depth estimation with lower computational costs, particularly in predicting fine geometric details. Group 1: Depth Estimation Overview - Depth estimation is the process of inferring the three-dimensional structure of objects in a real image, where higher accuracy allows for better environmental perception and world model reconstruction [1]. - InfiniDepth provides high-precision geometric structures, offering relative depth from monocular RGB images and generating ultra-high-resolution absolute depth when combined with LiDAR or sparse depth inputs [1]. Group 2: Methodological Inspiration - InfiniDepth draws inspiration from advancements in 3D reconstruction, specifically NeRF and PiFU, which demonstrate that scenes can be modeled as continuous functions rather than rigid 3D pixels, achieving high geometric detail with fewer parameters [2]. - The LIIF (Learning Local Implicit Fourier Representation) method introduces implicit functions to 2D images, treating them as continuous signals for arbitrary scale super-resolution, which InfiniDepth applies to depth map predictions [3]. Group 3: Key Innovations - InfiniDepth challenges traditional depth estimation methods that restrict output resolution to the input image size, proposing a neural implicit field model for depth that decouples resolution from input size [4]. - The method consists of three core steps: - Feature extraction using a visual encoder (DINOv3) to create a feature pyramid that captures both macro and micro information [5]. - Depth decoding through a lightweight decoder (MLP) that efficiently translates features into depth values [6]. - Infinite depth querying that intelligently generates additional query points in sparse areas to ensure uniform distribution of 3D point clouds [7]. Group 4: Performance Metrics - InfiniDepth demonstrates superior depth map quality at higher resolutions, achieving better point cloud results and improved effects in bird's-eye view (BEV) perspectives [10][11][14]. - A new testing dataset was created based on five AAA games to address the limitations of traditional low-resolution and sparse ground truth depth maps, which often fail to capture fine geometric structures [15]. Group 5: Statistical Performance - InfiniDepth achieved first place in 58 out of 60 statistical metrics, with two second-place finishes, showcasing its effectiveness compared to other methods [16].

Core Viewpoint - The article introduces Pixel-Perfect Depth (PPD), a novel monocular depth estimation model that addresses the issue of "flying pixels" prevalent in existing methods, enhancing the accuracy of depth perception in robotics and 3D reconstruction [4][7]. Group 1: Problem Identification - Current monocular depth estimation models face significant challenges, particularly the "flying pixels" problem, which leads to erroneous actions in robotic decision-making and distorted object outlines in 3D reconstruction [2][7]. - Discriminative models tend to produce averaged predictions at depth discontinuities due to their smoothing tendencies, while generative models, despite retaining more details, suffer from structural sharpness loss and geometric fidelity issues due to VAE compression [4][7]. Group 2: Proposed Solution - Pixel-Perfect Depth employs a diffusion generation approach directly in pixel space, effectively eliminating the flying pixel issue caused by VAE compression [4][7]. - The model integrates a semantic-guided diffusion Transformer (SP-DiT) that incorporates high-level semantic features from visual foundation models, enhancing both global structure understanding and detail recovery [4][5]. Group 3: Performance and Recognition - The proposed method achieves superior performance compared to all existing generative models in depth estimation tasks, marking a significant advancement in the field [7][11]. - The research has been recognized as a high-quality paper for NeurIPS 2025, highlighting its innovative approach to achieving pixel-perfect depth estimation [11].

Research Motivation and Contribution - The core issue in existing depth estimation methods is the "Flying Pixels" problem, which leads to erroneous actions in robotic decision-making and ghosting in 3D reconstruction [2] - The proposed method, Pixel-Perfect Depth (PPD), aims to eliminate artifacts caused by VAE compression by performing diffusion directly in pixel space [6] Innovation and Methodology - PPD introduces a novel diffusion model that operates in pixel space, addressing challenges of maintaining global semantic consistency and local detail accuracy [6][9] - The model incorporates a Semantics-Prompted Diffusion Transformer (SP-DiT) that enhances the modeling capabilities by integrating high-level semantic features during the diffusion process [9][16] Results and Performance - PPD outperforms existing generative depth estimation models across five public benchmarks, showing significant improvements in edge point cloud evaluation and producing depth maps with minimal "Flying Pixels" [14][20] - The model demonstrates exceptional zero-shot generalization capabilities, achieving superior performance without relying on pre-trained image priors [20][22] Experimental Analysis - A comprehensive ablation study indicates that the proposed SP-DiT significantly enhances performance metrics, with an 78% improvement in the AbsRel metric on the NYUv2 dataset compared to baseline models [25][26] - The introduction of a Cascaded DiT design improves computational efficiency by reducing inference time by 30% while maintaining high accuracy [26][27] Edge Point Cloud Evaluation - The model aims to generate pixel-perfect depth maps, addressing the challenge of evaluating edge accuracy through a newly proposed Edge-Aware Point Cloud Metric [28][30] - Experimental results confirm that PPD effectively avoids the "Flying Pixels" issue, demonstrating superior performance in edge accuracy compared to existing methods [28][34] Conclusion - PPD represents a significant advancement in depth estimation, providing high-quality outputs with sharp structures and clear edges, while minimizing artifacts [34][35] - The research opens new avenues for high-fidelity depth estimation based on diffusion models, emphasizing the importance of maintaining both global semantics and local geometric consistency [35]