We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc. Unlike previous methods which struggle with limited decomposability, unsatisfactory quality, and long optimization times, StdGEN features decomposability, effectiveness and efficiency; i.e., it generates intricately detailed 3D characters with separated semantic components such as the body, clothes, and hair, in three minutes. At the core of StdGEN is our proposed Semantic-aware Large Reconstruction Model (S-LRM), a transformer-based generalizable model that jointly reconstructs geometry, color and semantics from multi-view images in a feed-forward manner. A differentiable multilayer semantic surface extraction scheme is introduced to acquire meshes from hybrid implicit fields reconstructed by our S-LRM. Additionally, a specialized efficient multi-view diffusion model and an iterative multi-layer surface refinement module are integrated into the pipeline to facilitate high-quality, decomposable 3D character generation. Extensive experiments demonstrate our state-of-theart performance in 3D anime character generation, surpassing existing baselines by a significant margin in geometry, texture and decomposability. StdGEN offers ready-touse semantic-decomposed 3D characters and enables flexible customization for a wide range of applications. Project page: https://stdgen.github.io

Procedural Content Generation (PCG) is powerful in creating high-quality 3D contents, yet controlling it to produce desired shapes is difficult and often requires extensive parameter tuning. Inverse Procedural Content Generation aims to automatically find the best parameters under the input condition. However, existing sampling-based and neural network-based methods still suffer from numerous sample iterations or limited controllability. In this work, we present DI-PCG, a novel and efficient method for Inverse PCG from general image conditions. At its core is a lightweight diffusion transformer model, where PCG parameters are directly treated as the denoising target and the observed images as conditions to control parameter generation. DI-PCG is efficient and effective. With only 7.6M network parameters and 30 GPU hours to train, it demonstrates superior performance in recovering parameters accurately, and generalizing well to in-the-wild images. Quantitative and qualitative experiment results validate the effectiveness of DI-PCG in inverse PCG and image-to-3D generation tasks. DI-PCG offers a promising approach for efficient inverse PCG and represents a valuable exploration step towards a 3D generation path that models how to construct a 3D asset using parametric models.

Diffusion-based video depth estimation methods have achieved remarkable success with strong generalization ability. However, predicting depth for long videos remains challenging. Existing methods typically split videos into overlapping sliding windows, leading to accumulated scale discrepancies across different windows, particularly as the number of windows increases. Additionally, these methods rely solely on 2D diffusion priors, overlooking the inherent 3D geometric structure of video depths, which results in geometrically inconsistent predictions. In this paper, we propose DepthSync, a novel, training-free framework using diffusion guidance to achieve scale- and geometry-consistent depth predictions for long videos. Specifically, we introduce scale guidance to synchronize the depth scale across windows and geometry guidance to enforce geometric alignment within windows based on the inherent 3D constraints in video depths. These two terms work synergistically, steering the denoising process toward consistent depth predictions. Experiments on various datasets validate the effectiveness of our method in producing depth estimates with improved scale and geometry consistency, particularly for long videos.

We present CHARM, a novel parametric representation and generative framework for anime hairstyle modeling. While traditional hair modeling methods focus on realistic hair using strand-based or volumetric representations, anime hairstyle exhibits highly stylized, piecewise-structured geometry that challenges existing techniques. Existing works often rely on dense mesh modeling or hand-crafted spline curves, making them inefficient for editing and unsuitable for scalable learning. CHARM introduces a compact, invertible control-point-based parameterization, where a sequence of control points represents each hair card, and each point is encoded with only five geometric parameters. This efficient and accurate representation supports both artist-friendly design and learning-based generation. Built upon this representation, CHARM introduces an autoregressive generative framework that effectively generates anime hairstyles from input images or point clouds. By interpreting anime hairstyles as a sequential “hair language”, our autoregressive transformer captures both local geometry and global hairstyle topology, resulting in high-fidelity anime hairstyle creation. To facilitate both training and evaluation of anime hairstyle generation, we construct AnimeHair, a large-scale dataset of 37K high-quality anime hairstyles with separated hair cards and processed mesh data. Extensive experiments demonstrate state-of-the-art performance of CHARM in both reconstruction accuracy and generation quality, offering an expressive and scalable solution for anime hairstyle modeling. Project page: https://hyzcluster.github.io/charm

We present Assembler, a scalable and generalizable framework for 3D part assembly that reconstructs complete objects from input part meshes and a reference image. Unlike prior approaches that mostly rely on deterministic part pose prediction and category-specific training, Assembler is designed to handle diverse, in-the-wild objects with varying part counts, geometries, and structures. It addresses the core challenges of scaling to general 3D part assembly through innovations in task formulation, representation, and data. First, Assembler casts part assembly as a generative problem and employs diffusion models to sample plausible configurations, effectively capturing ambiguities arising from symmetry, repeated parts, and multiple valid assemblies. Second, we introduce a novel shape-centric representation based on sparse anchor point clouds, enabling scalable generation in Euclidean space and avoiding the limitations of abstract SE(3) pose prediction. Third, we construct a large-scale dataset of over 320K diverse part-object assemblies using a synthesis and filtering pipeline built on existing 3D shape repositories. Assembler achieves state-of-the-art performance on PartNet and is the first to demonstrate high-quality assembly for complex, real-world objects. Based on Assembler, we further introduce an interesting part-aware 3D modeling system that generates high-resolution, editable objects from images, demonstrating potential for interactive and compositional design. Project page: https://assembler3d.github.io/

The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. These methods excel in producing complete and smooth results for floor and wall areas. However, they struggle to capture complex surfaces with high-frequency structures due to the inadequate neural representation and the inaccurately predicted normal priors. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations. To improve the capacity of the implicit representation, we propose a hybrid architecture to represent low-frequency and high-frequency regions separately. To enhance the normal priors, we introduce a simple yet effective image sharpening and denoising technique, coupled with a network that estimates the pixel-wise uncertainty of the predicted surface normal vectors. Identifying such uncertainty can prevent our model from being misled by unreliable surface normal supervisions that hinder the accurate reconstruction of intricate geometries. Experiments on the benchmark datasets show that our method outperforms existing methods in terms of reconstruction quality. Furthermore, the proposed method also generalizes well to real-world indoor scenarios captured by our hand-held mobile phones.

Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects. Specifically, we utilize a pre-trained diffusion model to fill in the hidden areas of 2D images. Then we use these in-painted images to optimize a neural implicit surface representation for each instance for 3D reconstruction. Since creating the in-painting masks needed for this process is tricky, we adopt a human-in-the-loop strategy that involves very little human engagement to generate high-quality masks. Moreover, some parts of objects can be totally hidden because the videos are usually shot from limited perspectives. To ensure recovering these invisible areas, we develop a cascaded network architecture for predicting signed distance field, making use of different frequency bands of positional encoding and maintaining overall smoothness. Besides the commonly used rendering loss, Eikonal loss, and silhouette loss, we adopt a CLIP-based semantic consistency loss to guide the surface from unseen camera angles. Experiments on ScanNet scenes show that our proposed framework achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos. Code: https://github.com/THU-LYJ-Lab/O2-Recon.

Depth estimation is a crucial task in computer vision, applicable to various domains such as 3D reconstruction, robotics, and autonomous driving. In particular, thermal-based depth estimation has unique advantages, including night-time vision. However, the existing depth estimation method remains challenging in robust generalization due to limited data resources and spectral differences between thermal and RGB images. In this paper, we present a self-supervised approach to enhance thermal-based depth estimation by leveraging pre-trained visual models initially designed for RGB data. In detail, we design a novel two-stage training strategy, incorporating Low-rank Adapters and Convolutional Adapters, which not only significantly improves accuracy and robustness but also enables impressive zero-shot generalization capabilities. Our method outperforms existing thermal-based depth estimation models, opening new possibilities for cross-modal applications in computer vision and robotics research.

This paper presents a flexible representation of neural radiance fields based on multi-plane images (MPI), for high-quality view synthesis of complex scenes. MPI with Normalized Device Coordinate (NDC) parameterization is widely used in NeRF learning for its simple definition, easy calculation, and powerful ability to represent unbounded scenes. However, existing NeRF works that adopt MPI representation for novel view synthesis can only handle simple forward-facing unbounded scenes (e.g., the scenes in the LLFF dataset), where the input cameras are all observing in similar directions with small relative translations. Hence, extending these MPIbased methods to more complex scenes like large-range or even 360-degree scenes is very challenging. In this paper, we explore the potential of MPI and show that MPI can synthesize high-quality novel views of complex scenes with diverse camera distributions and view directions, which are not only limited to simple forward-facing scenes. Our key idea is to encode the neural radiance field with multiple MPIs facing different directions and blend them with an adaptive blending operation. For each region of the scene, the blending operation gives larger blending weights to those advantaged MPIs with stronger local representation abilities while giving lower weights to those with weaker representation abilities. Such blending operation automatically modulates the multiple MPIs to appropriately represent the diverse local density and color information. Experiments on the KITTI dataset and ScanNet dataset demonstrate that our proposed MMPI synthesizes high-quality images from diverse camera pose distributions and is fast to train, outperforming the previous fast-training NeRF methods for novel view synthesis. Moreover, we show that MMPI can encode extremely long trajectories and produce novel view renderings, demonstrating its potential in applications like autonomous driving. Our demo video is available at https://youtube.com/watch?v=mbNKwN5urC8.

This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and establishes a plane reconstruction pipeline based on monocular geometric cues, resulting in accurate, robust and scalable 3D plane detection and reconstruction in the wild. Specifically, we first leverage large-scale pre-trained neural networks to obtain the depth and surface normals from a single image. These monocular geometric cues are then incorporated into a proximity-guided RANSAC framework to sequentially fit each plane instance. We exploit effective 3D point proximity and model such proximity via a graph within RANSAC to guide the plane fitting from noisy monocular depths, followed by image-level multi-plane joint optimization to improve the consistency among all plane instances. We further design a simple but effective pipeline to extend this single-view solution to sparse-view 3D plane reconstruction. Extensive experiments on a list of datasets demonstrate our superior zero-shot generalizability over baselines, achieving state-of-the-art plane reconstruction performance in a transferring setting. Our code is available at https://github.com/thuzhaowang/MonoPlane.

We introduce AlphaTablets, a novel and generic representation of 3D planes that features continuous 3D surface and precise boundary delineation. By representing 3D planes as rectangles with alpha channels, AlphaTablets combine the advantages of current 2D and 3D plane representations, enabling accurate, consistent and flexible modeling of 3D planes. We derive differentiable rasterization on top of AlphaTablets to efficiently render 3D planes into images, and propose a novel bottom-up pipeline for 3D planar reconstruction from monocular videos. Starting with 2D superpixels and geometric cues from pre-trained models, we initialize 3D planes as AlphaTablets and optimize them via differentiable rendering. An effective merging scheme is introduced to facilitate the growth and refinement of AlphaTablets. Through iterative optimization and merging, we reconstruct complete and accurate 3D planes with solid surfaces and clear boundaries. Extensive experiments on the ScanNet dataset demonstrate state-of-the-art performance in 3D planar reconstruction, underscoring the great potential of AlphaTablets as a generic 3D plane representation for various applications.

Low-light visual perception, such as SLAM or SfM at night, has received increasing attention, in which keypoint detection and local feature description play an important role. Both handcraft designs and machine learning methods have been widely studied for local feature detection and description, however, the performance of existing methods degrades in the extreme low-light scenarios in a certain degree, due to the low signal-to-noise ratio in images. To address this challenge, images in RAW format that retain more raw sensing information have been considered in recent works with a denoise-then-detect scheme. However, existing denoising methods are still insufficient for RAW images and heavily time-consuming, which limits the practical applications of such scheme. In this paper, we propose DarkFeat, a deep learning model which directly detects and describes local features from extreme low-light RAW images in an end-to-end manner. A novel noise robustness map and selective suppression constraints are proposed to effectively mitigate the influence of noise and extract more reliable keypoints. Furthermore, a customized pipeline of synthesizing dataset containing low-light RAW image matching pairs is proposed to extend end-to-end training. Experimental results show that DarkFeat achieves state-of-the-art performance on both indoor and outdoor parts of the challenging MID benchmark, outperforms the denoise-then-detect methods and significantly reduces computational costs up to 70%. Code is available at https://github.com/THU-LYJ-Lab/DarkFeat.

Next best view (NBV) is a technology that finds the best view sequence for sensor to perform scanning based on partial information, which is the core part for robot active reconstruction. Traditional works are mostly based on the evaluation of candidate views through time-consuming volu-metric transformation and ray casting, which heavily limits the applications of NBV. Recent deep learning based NBV methods aim to approximately learn the evaluation function by large-scale training, and improve both the effectiveness and efficiency of NBV. However, these methods force the network to regress the exact groundtruth value of each candidate view, which is much harder than simply ranking all the candidate views. Besides, most previous NBV works assume perfect sensing and perform in simulation environments, lacking real application abilities. In this paper, we propose a novel double branch NBV network, DB-NBV, to utilize the ranking process together with the evaluation process. We further design a real NBV robot and a pipeline to conduct real active reconstruction. Experiments on both simulation and real robot show that our method achieves the best performance and can be applied to real application with high accuracy and speed.

Cartoon is a common form of art in our daily life and automatic generation of cartoon images from photos is highly desirable. However, state-of-the-art single-style methods can only generate one style of cartoon images from photos and existing multi-style image style transfer methods still struggle to produce high-quality cartoon images due to their highly simplified and abstract nature. In this article, we propose a novel multi-style generative adversarial network (GAN) architecture, called MS-CartoonGAN, which can transform photos into multiple cartoon styles. MS-CartoonGAN uses only unpaired photos and cartoon images of multiple styles for training. To achieve this, we propose to use (1) a hierarchical semantic loss with sparse regularization to retain semantic content and recover flat shading in different abstract levels, (2) a new edge-promoting adversarial loss for producing fine edges, and (3) a style loss to enhance the difference between output cartoon styles and make training process more stable. We also develop a multi-domain architecture, where the generator consists of a shared encoder and multiple decoders for different cartoon styles, along with multiple discriminators for individual styles. By observing that cartoon images drawn by different artists have their unique styles while sharing some common characteristics, our shared network architecture exploits the common characteristics of cartoon styles, achieving better cartoonization and being more efficient than single-style cartoonization. We show that our multi-domain architecture can theoretically guarantee to output desired multiple cartoon styles. Through extensive experiments including a user study, we demonstrate the superiority of the proposed method, outperforming state-of-the-art single-style and multi-style image style transfer methods.

In this work, we present a new multi-view depth estimation method that utilizes both conventional SfM reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF). Unlike existing neural network based optimization method that relies on estimated correspondences, our method directly optimizes over implicit volumes, eliminating the challenging step of matching pixels in indoor scenes. The key to our approach is to utilize the learning-based priors to guide the optimization process of NeRF. Our system firstly adapts a monocular depth network over the target scene by finetuning on its sparse SfM reconstruction. Then, we show that the shape-radiance ambiguity of NeRF still exists in indoor environments and propose to address the issue by employing the adapted depth priors to monitor the sampling process of volume rendering. Finally, a per-pixel confidence map acquired by error computation on the rendered image can be used to fur ther improve the depth quality. Experiments show that our proposed framework significantly outperforms state-of-the-art methods on indoor scenes, with surprising findings presented on the effectiveness of correspondence-based opti-mization and NeRF-based optimization over the adapted depth priors. In addition, we show that the guided opti-mization scheme does not sacrifice the original synthesis capability of neural radiance fields, improving the rendering quality on both seen and novel views. Code is available at https://github.com/weiyithu/NerfingMVS.

In this paper, we introduce a deep multi-view stereo (MVS) system that jointly predicts depths, surface normals and per-view confidence maps. The key to our approach is a novel solver that iteratively solves for per-view depth map and normal map by optimizing an energy potential based on the locally planar assumption. Specifically, the algorithm updates depth map by propagating from neigh-boring pixels with slanted planes, and updates normal map with local probabilistic plane fitting. Both two steps are monitored by a customized confidence map. This solver is not only effective as a post-processing tool for plane-based depth refinement and completion, but also differentiable such that it can be efficiently integrated into deep learning pipelines. Our multi-view stereo system employs multiple optimization steps of the solver over the initial prediction of depths and surface normals. The whole system can be trained end-to-end, decoupling the challenging problem of matching pixels within poorly textured regions from the cost-volume based neural network. Experimental results on ScanNet and RGB-D Scenes V2 demonstrate state-of-the-art performance of the proposed deep MVS system on multi-view depth estimation, with our proposed solver consistently improving the depth quality over both conventional and deep learning based MVS pipelines. Code is available at https://github.com/thuzhaowang/idn-solver.

Over-segmenting a video into supervoxels has strong potential to reduce the complexity of downstream computer vision applications. Content-sensitive supervoxels (CSSs) are typically smaller in content-dense regions (i.e., with high variation of appearance and/or motion) and larger in content-sparse regions. In this paper, we propose to compute feature-aware CSSs (FCSSs) that are regularly shaped 3D primitive volumes well aligned with local object/region/motion boundaries in video. To compute FCSSs, we map a video to a 3D manifold embedded in a combined color and spatiotemporal space, in which the volume elements of video manifold give a good measure of the video content density. Then any uniform tessellation on video manifold can induce CSS in the video. Our idea is that among all possible uniform tessellations on the video manifold, FCSS finds one whose cell boundaries well align with local video boundaries. To achieve this goal, we propose a novel restricted centroidal Voronoi tessellation method that simultaneously minimizes the tessellation energy (leading to uniform cells in the tessellation) and maximizes the average boundary distance (leading to good local feature alignment). Theoretically our method has an optimal competitive ratio O(1), and its time and space complexities are O(NK) and O(N+K) for computing K supervoxels in an N-voxel video. We also present a simple extension of FCSS to streaming FCSS for processing long videos that cannot be loaded into main memory at once. We evaluate FCSS, streaming FCSS and ten representative supervoxel methods on four video datasets and two novel video applications. The results show that our method simultaneously achieves state-of-the-art performance with respect to various evaluation criteria.

In this work, we tackle the essential problem of scale inconsistency for self supervised joint depth-pose learning. Most existing methods assume that a consistent scale of depth and pose can be learned across all input samples, which makes the learning problem harder, resulting in degraded performance and limited generalization in indoor environments and long-sequence visual odometry application. To address this issue, we propose a novel system that explicitly disentangles scale from the network estimation. Instead of relying on PoseNet architecture, our method recovers relative pose by directly solving fundamental matrix from dense optical flow correspondence and makes use of a two-view triangulation module to recover an up-to-scale 3D structure. Then, we align the scale of the depth prediction with the triangulated point cloud and use the transformed depth map for depth error computation and dense reprojection check. Our whole system can be jointly trained end-to-end. Extensive experiments show that our system not only reaches state-of-the-art performance on KITTI depth and flow estimation, but also significantly improves the generalization ability of existing self-supervised depth-pose learning methods under a variety of challenging scenarios, and achieves state-of-the-art results among self-supervised learning-based methods on KITTI Odometry and NYUv2 dataset. Furthermore, we present some interesting findings on the limitation of PoseNet-based relative pose estimation methods in terms of generalization ability. Code is available at https://github.com/B1ueber2y/TrianFlow.

Motion planning for robots of high degrees-of-freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space $\mathcal{C}$ as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in $\mathcal{C}$. In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single-classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented.

The Next Best View (NBV) problem is important in the active robotic reconstruction. It enables the robot system to perform scanning actions in a reasonable view sequence, and fulfil the reconstruction task in an effective way. Previous works mainly follow the volumetric methods, which convert the point cloud information collected by sensors into a voxel representation space and evaluate candidate views through ray casting simulations to pick the NBV. However, the process of volumetric data transformation and ray casting is often time-consuming. To address this issue, in this paper, we propose a point cloud based deep neural network called PC-NBV to achieve efficient view planning without these computationally expensive operations. The PC-NBV network takes the raw point cloud data and current view selection states as input, and then directly predicts the information gain of all candidate views. By avoiding costly data transformation and ray casting, and utilizing powerful neural network to learn structure priors from point cloud, our method can achieve efficient and effective NBV planning. Experiments on multiple datasets show the proposed method outperforms state-of-the-art NBV methods, giving better views for robot system with much less inference time. Furthermore, we demonstrate the robustness of our method against noise and the ability to extend to multi-view system, making it more applicable for various scenarios.

Rapid development of artificial intelligence motivates researchers to expand the capabilities of intelligent and autonomous robots. In many robotic applications, robots are required to make planning decisions based on perceptual information to achieve diverse goals in an efficient and effective way. The planning problem has been investigated in active robot vision, in which a robot analyzes its environment and its own state in order to move sensors to obtain more useful information under certain constraints. View planning, which aims to find the best view sequence for a sensor, is one of the most challenging issues in active robot vision. The quality and efficiency of view planning are critical for many robot systems and are influenced by the nature of their tasks, hardware conditions, scanning states, and planning strategies. In this paper, we first summarize some basic concepts of active robot vision, and then review representative work on systems, algorithms and applications from four perspectives: object reconstruction, scene reconstruction, object recognition, and pose estimation. Finally, some potential directions are outlined for future work.

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single groundtruth shape because the back part is occluded. In this work, we first introduce a conditional generative network to model the uncertainty for single-view reconstruction. Then, we formulate the task of multi-view reconstruction as taking the intersection of the predicted shape spaces on each single image. We design new differentiable guidance including the front constraint, the diversity constraint, and the consistency loss to enable effective single-view conditional generation and multi-view synthesis. Experimental results and ablation studies show that our proposed approach outperforms state-of-the-art methods on 3D reconstruction test error and demonstrates its generalization ability on real world data.

We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, greatly reducing proposals with low objectness.

Recently some pioneering works such as PointNet and Point-Net++ successfully introduce deep learning architectures into point cloud analysis. These novel networks take irregular point cloud (i.e., a set of unordered points) as input, in which each point is represented by (x, y, z) coordinates plus some attributes including color, normal, and other local or global features. Despite of their success on various tasks, the computational cost of these networks become extremely high for large-scale point clouds, e.g., containing hundreds of thousands or millions of points. Instead of uniform down-sampling, in this paper, we propose a simple and novel filter that can efficiently filter any large-scale point cloud into thousands of representative points embedded in a high dimensional feature space, such that without changing the existing deep learning networks, simply using our filter as a preprocess, these existing models can work with large-scale point clouds. Experimental results show that by using our proposed filter, the computational cost (measured by floating-point operation) of PointNet and PointNet++ is reduced 30-60 times and the accuracy of semantic segmentation (measured by mean IoU) on ScanNet dataset is improved 5%-15% averagely.