Guoping Wang

Mai Su, Qihan Yu, Zhongtao Wang et al.

3D Gaussian Splatting enables efficient optimization and high-quality rendering, yet accurate surface reconstruction remains challenging. Prior methods improve surface reconstruction by refining Gaussian depth estimates, either via multi-view geometric consistency or through monocular depth priors. However, multi-view constraints become unreliable under large geometric discrepancies, while monocular priors suffer from scale ambiguity and local inconsistency, ultimately leading to inaccurate Gaussian depth supervision. To address these limitations, we introduce a Gaussian visibility-aware multi-view geometric consistency constraint that aggregates the visibility of shared Gaussian primitives across views, enabling more accurate and stable geometric supervision. In addition, we propose a progressive quadtree-calibrated Monocular depth constraint that performs block-wise affine calibration from coarse to fine spatial scales, mitigating the scale ambiguity of depth priors while preserving fine-grained surface details. Extensive experiments on DTU and TNT datasets demonstrate consistent improvements in geometric accuracy over prior Gaussian-based and implicit surface reconstruction methods. Codes are available at an anonymous repository: https://github.com/GVGScode/GVGS.

Bo Pang, Zhongtian Zheng, Guoping Wang et al.

We present GeGnn, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on computing the geodesic distance between a single source and all destinations, which has linear complexity at least or require a long precomputation time. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space and compute the geodesic distance between a pair of points using the corresponding embedding vectors and a lightweight decoding function. To facilitate the learning of the embedding, we propose novel graph convolution and graph pooling modules that incorporate local geodesic information and are verified to be much more effective than previous designs. After training, our method requires only one forward pass of the network per mesh as precomputation. Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude while achieving comparable or better accuracy. Additionally, our method exhibits robustness on noisy and incomplete meshes and strong generalization ability on out-of-distribution meshes. The code and pretrained model can be found on https://github.com/IntelligentGeometry/GeGnn.

Bo Pang, Zhongtian Zheng, Yilong Li et al.

The discrete Laplacian operator holds a crucial role in 3D geometry processing, yet it is still challenging to define it on point clouds. Previous works mainly focused on constructing a local triangulation around each point to approximate the underlying manifold for defining the Laplacian operator, which may not be robust or accurate. In contrast, we simply use the K-nearest neighbors (KNN) graph constructed from the input point cloud and learn the Laplacian operator on the KNN graph with graph neural networks (GNNs). However, the ground-truth Laplacian operator is defined on a manifold mesh with a different connectivity from the KNN graph and thus cannot be directly used for training. To train the GNN, we propose a novel training scheme by imitating the behavior of the ground-truth Laplacian operator on a set of probe functions so that the learned Laplacian operator behaves similarly to the ground-truth Laplacian operator. We train our network on a subset of ShapeNet and evaluate it across a variety of point clouds. Compared with previous methods, our method reduces the error by an order of magnitude and excels in handling sparse point clouds with thin structures or sharp features. Our method also demonstrates a strong generalization ability to unseen shapes. With our learned Laplacian operator, we further apply a series of Laplacian-based geometry processing algorithms directly to point clouds and achieve accurate results, enabling many exciting possibilities for geometry processing on point clouds. The code and trained models are available at https://github.com/IntelligentGeometry/NeLo.

Zhongtao Wang, Huishan Au, Yilong Li et al.

We present BlitzGS, a distributed 3DGS framework that reduces active Gaussian workload for fast city-scale reconstruction. BlitzGS manages this workload at three coupled levels. At the system level, the framework shards Gaussians across GPUs by index parity rather than spatial blocks. This approach mitigates the cross-block visibility redundancy inherent in spatial partitioning. Furthermore, it distributes each rendering step through a single cross-GPU exchange that routes projected Gaussians to their tile owners. At the model level, scheduled importance-scoring passes shrink the global Gaussian population. During these passes, the framework generates a per-Gaussian visibility weight to bias density-control updates toward contributing primitives and a per-view importance mask for the view-level renderer. At the view level, BlitzGS trims each camera's active set with a distance-based LOD gate to exclude excessively fine primitives for the current frustum and the importance-based culling mask to skip Gaussians with negligible cross-view contribution. On large-scale benchmarks, BlitzGS matches the rendering quality of recent large-scale baselines while delivering an order-of-magnitude speedup, training city-scale scenes in tens of minutes. Our code is available at https: //github.com/AkierRaee/BlitzGS.

Xutong Jin, Fei Zhu, Guoping Wang et al.

Interactive synthesis of physical sound effects is crucial in digital media production. Sound radiation simulation, a key component of physically based sound synthesis, has posed challenges in the context of complex object boundaries. Previous methods, such as ghost cell-based finite-difference time-domain (FDTD) wave solver, have struggled to address these challenges, leading to large errors and failures in complex boundaries because of the limitation of ghost cells. We present SonicRadiation, a hybrid numerical solution capable of handling complex and dynamic object boundaries in sound radiation simulation without relying on ghost cells. We derive a consistent formulation to connect the physical quantities on grid cells in FDTD with the boundary elements in the time-domain boundary element method (TDBEM). Hereby, we propose a boundary grid synchronization strategy to seamlessly integrate TDBEM with FDTD while maintaining high numerical accuracy. Our method holds both advantages from the accuracy of TDBEM for the near-field and the efficiency of FDTD for the far-field. Experimental results demonstrate the superiority of our method in sound radiation simulation over previous approaches in terms of accuracy and efficiency, particularly in complex scenes, further validating its effectiveness.

Zhiru Wang, Shiyun Xie, Chengwei Pan et al.

Recently, the 3D Gaussian Splatting (3D-GS) method has achieved great success in novel view synthesis, providing real-time rendering while ensuring high-quality rendering results. However, this method faces challenges in modeling specular reflections and handling anisotropic appearance components, especially in dealing with view-dependent color under complex lighting conditions. Additionally, 3D-GS uses spherical harmonic to learn the color representation, which has limited ability to represent complex scenes. To overcome these challenges, we introduce Lantent-SpecGS, an approach that utilizes a universal latent neural descriptor within each 3D Gaussian. This enables a more effective representation of 3D feature fields, including appearance and geometry. Moreover, two parallel CNNs are designed to decoder the splatting feature maps into diffuse color and specular color separately. A mask that depends on the viewpoint is learned to merge these two colors, resulting in the final rendered image. Experimental results demonstrate that our method obtains competitive performance in novel view synthesis and extends the ability of 3D-GS to handle intricate scenarios with specular reflections.

Yiming Zhao, Dewen Guo, Zhouhui Lian et al.

To bridge the gap between artists and non-specialists, we present a unified framework, Neural-Polyptych, to facilitate the creation of expansive, high-resolution paintings by seamlessly incorporating interactive hand-drawn sketches with fragments from original paintings. We have designed a multi-scale GAN-based architecture to decompose the generation process into two parts, each responsible for identifying global and local features. To enhance the fidelity of semantic details generated from users' sketched outlines, we introduce a Correspondence Attention module utilizing our Reference Bank strategy. This ensures the creation of high-quality, intricately detailed elements within the artwork. The final result is achieved by carefully blending these local elements while preserving coherent global consistency. Consequently, this methodology enables the production of digital paintings at megapixel scale, accommodating diverse artistic expressions and enabling users to recreate content in a controlled manner. We validate our approach to diverse genres of both Eastern and Western paintings. Applications such as large painting extension, texture shuffling, genre switching, mural art restoration, and recomposition can be successfully based on our framework.

Yifan Gao, Lu Zou, Zhangjin Huang et al.

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible optimization signals in shared modules, resulting in gradient conflicts and negative transfer during training. To address this challenge, we first introduce gradient-based diagnostics to quantify module-level cross-category contention. Building on results of diagnostics, we propose DecomPose, a difficulty-aware decomposition framework that mitigates optimization contention via: (1) difficulty-aware gradient decoupling, which groups categories using a data-driven difficulty proxy and routes each instance to a group-specific correspondence branch to isolate incompatible updates; and (2) stability-driven asymmetric branching, which assigns higher-capacity branches to structurally simple categories as stable optimization anchors while constraining complex categories with lightweight branches to suppress noisy updates and alleviate negative transfer. Extensive experiments on REAL275, CAMERA25, and HouseCat6D demonstrate that DecomPose effectively reduces cross-category optimization contention and delivers superior pose estimation performance across multiple benchmarks.

Bo Pang, Chenxi Xu, Jierui Ren et al.

Understanding the physical world requires perceptual models grounded in physical laws rather than mere statistical correlations. However, existing multimodal learning frameworks, focused on vision and language, lack physical consistency and overlook the intrinsic causal relationships among an object's geometry, material, vibration modes, and the sounds it produces. We introduce VibraVerse, a large-scale geometry-acoustics alignment dataset that explicitly bridges the causal chain from 3D geometry -> physical attributes -> modal parameters -> acoustic signals. Each 3D model has explicit physical properties (density, Young's modulus, Poisson's ratio) and volumetric geometry, from which modal eigenfrequencies and eigenvectors are computed for impact sound synthesis under controlled excitations. To establish this coherence, we introduce CLASP, a contrastive learning framework for cross-modal alignment that preserves the causal correspondence between an object's physical structure and its acoustic response. This framework enforces physically consistent alignment across modalities, ensuring that every sample is coherent, traceable to the governing equations, and embedded within a unified representation space spanning shape, image, and sound. Built upon VibraVerse, we define a suite of benchmark tasks for geometry-to-sound prediction, sound-guided shape reconstruction, and cross-modal representation learning. Extensive validations on these tasks demonstrate that models trained on VibraVerse exhibit superior accuracy, interpretability, and generalization across modalities. These results establish VibraVerse as a benchmark for physically consistent and causally interpretable multimodal learning, providing a foundation for sound-guided embodied perception and a deeper understanding of the physical world. The dataset will be open-sourced.

Zhongtao Wang, Jiaqi Dai, Qingtian Zhu et al.

Multi-period image collections are common in real-world applications. Cities are re-scanned for mapping, construction sites are revisited for progress tracking, and natural regions are monitored for environmental change. Such data form multi-period scenes, where geometry and appearance evolve. Reconstructing such scenes is an important yet underexplored problem. Existing pipelines rely on incompatible assumptions: static and in-the-wild methods enforce a single geometry, while dynamic ones assume smooth motion, both failing under long-term, discontinuous changes. To solve this problem, we introduce ChronoGS, a temporally modulated Gaussian representation that reconstructs all periods within a unified anchor scaffold. It's also designed to disentangle stable and evolving components, achieving temporally consistent reconstruction of multi-period scenes. To catalyze relevant research, we release ChronoScene dataset, a benchmark of real and synthetic multi-period scenes, capturing geometric and appearance variation. Experiments demonstrate that ChronoGS consistently outperforms baselines in reconstruction quality and temporal consistency. Our code and the ChronoScene dataset are publicly available at https://github.com/ZhongtaoWang/ChronoGS.

Zizhuang Wei, Qingtian Zhu, Chen Min et al.

In this paper, we present a novel recurrent multi-view stereo network based on long short-term memory (LSTM) with adaptive aggregation, namely AA-RMVSNet. We firstly introduce an intra-view aggregation module to adaptively extract image features by using context-aware convolution and multi-scale aggregation, which efficiently improves the performance on challenging regions, such as thin objects and large low-textured surfaces. To overcome the difficulty of varying occlusion in complex scenes, we propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, which is able to preserve better-matched pairs among all views. The two proposed adaptive aggregation modules are lightweight, effective and complementary regarding improving the accuracy and completeness of 3D reconstruction. Instead of conventional 3D CNNs, we utilize a hybrid network with recurrent structure for cost volume regularization, which allows high-resolution reconstruction and finer hypothetical plane sweep. The proposed network is trained end-to-end and achieves excellent performance on various datasets. It ranks $1^{st}$ among all submissions on Tanks and Temples benchmark and achieves competitive results on DTU dataset, which exhibits strong generalizability and robustness. Implementation of our method is available at https://github.com/QT-Zhu/AA-RMVSNet.

Jianfeng Yan, Zizhuang Wei, Hongwei Yi et al.

In this paper, we propose an efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely $D^{2}$HC-RMVSNet, for accurate dense point cloud reconstruction. Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a HU-LSTM (Hybrid U-LSTM) to regularize 3D matching volume into predicted depth map, which efficiently aggregates different scale information by coupling LSTM and U-Net architecture. To further improve the accuracy and completeness of reconstructed point clouds, we leverage a dynamic consistency checking strategy instead of prefixed parameters and strategies widely adopted in existing methods for dense point cloud reconstruction. In doing so, we dynamically aggregate geometric consistency matching error among all the views. Our method ranks \textbf{$1^{st}$} on the complex outdoor \textsl{Tanks and Temples} benchmark over all the methods. Extensive experiments on the in-door DTU dataset show our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only $19.4\%$ of R-MVSNet memory consumption. The codebase is available at \hyperlink{https://github.com/yhw-yhw/D2HC-RMVSNet}{https://github.com/yhw-yhw/D2HC-RMVSNet}.

Yu Chen, Shuhan Shen, Yisong Chen et al.

While Structure from Motion (SfM) achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. In this work, large scale SfM is deemed as a graph problem, and we tackle it in a divide-and-conquer manner. Firstly, the images clustering algorithm divides images into clusters with strong connectivity, leading to robust local reconstructions. Then followed with an image expansion step, the connection and completeness of scenes are enhanced by expanding along with a maximum spanning tree. After local reconstructions, we construct a minimum spanning tree (MinST) to find accurate similarity transformations. Then the MinST is transformed into a Minimum Height Tree (MHT) to find a proper anchor node and is further utilized to prevent error accumulation. When evaluated on different kinds of datasets, our approach shows superiority over the state-of-the-art in accuracy and efficiency. Our algorithm is open-sourced at https://github.com/AIBluefisher/GraphSfM.

Hongwei Yi, Zizhuang Wei, Mingyu Ding et al.

n this paper, we propose an effective and efficient pyramid multi-view stereo (MVS) net with self-adaptive view aggregation for accurate and complete dense point cloud reconstruction. Different from using mean square variance to generate cost volume in previous deep-learning based MVS methods, our \textbf{VA-MVSNet} incorporates the cost variances in different views with small extra memory consumption by introducing two novel self-adaptive view aggregations: pixel-wise view aggregation and voxel-wise view aggregation. To further boost the robustness and completeness of 3D point cloud reconstruction, we extend VA-MVSNet with pyramid multi-scale images input as \textbf{PVA-MVSNet}, where multi-metric constraints are leveraged to aggregate the reliable depth estimation at the coarser scale to fill in the mismatched regions at the finer scale. Experimental results show that our approach establishes a new state-of-the-art on the \textsl{\textbf{DTU}} dataset with significant improvements in the completeness and overall quality, and has strong generalization by achieving a comparable performance as the state-of-the-art methods on the \textsl{\textbf{Tanks and Temples}} benchmark. Our codebase is at \hyperlink{https://github.com/yhw-yhw/PVAMVSNet}{https://github.com/yhw-yhw/PVAMVSNet}

Rui Su, Honghao Dong, Haojie Jin et al.

Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature grid representations often suffer from substantial memory footprint, posing a significant bottleneck for modern parallel computing hardware. In this paper, we present neural vertex features, a generalized formulation of learnable representation for neural rendering tasks involving explicit mesh surfaces. Instead of uniformly distributing neural features throughout 3D space, our method stores learnable features directly at mesh vertices, leveraging the underlying geometry as a compact and structured representation for neural processing. This not only optimizes memory efficiency, but also improves feature representation by aligning compactly with the surface using task-specific geometric priors. We validate our neural representation across diverse neural rendering tasks, with a specific emphasis on neural radiosity. Experimental results demonstrate that our method reduces memory consumption to only one-fifth (or even less) of grid-based representations, while maintaining comparable rendering quality and lowering inference overhead.

Zhongtao Wang, Xizhe Cao, Yisong Chen et al.

Semantic segmentation of remote sensing imagery demands precise spatial boundaries and robust intra-class consistency, challenging conventional hierarchical models. To address limitations arising from spatial domain feature fusion and insufficient receptive fields, this paper introduces SAIP-Net, a novel frequency-aware segmentation framework that leverages Spectral Adaptive Information Propagation. SAIP-Net employs adaptive frequency filtering and multi-scale receptive field enhancement to effectively suppress intra-class feature inconsistencies and sharpen boundary lines. Comprehensive experiments demonstrate significant performance improvements over state-of-the-art methods, highlighting the effectiveness of spectral-adaptive strategies combined with expanded receptive fields for remote sensing image segmentation.

Chenxiao Hu, Meng Gai, Guoping Wang et al.

We present a real-time global illumination approach along with a pipeline for dynamic 3D Gaussian models and meshes. Building on a formulated surface light transport model for 3D Gaussians, we address key performance challenges with a fast compound stochastic ray-tracing algorithm and an optimized 3D Gaussian rasterizer. Our pipeline integrates multiple real-time techniques to accelerate performance and achieve high-quality lighting effects. Our approach enables real-time rendering of dynamic scenes with interactively editable materials and dynamic lighting of diverse multi-lights settings, capturing mutual multi-bounce light transport (indirect illumination) between 3D Gaussians and mesh. Additionally, we present a real-time renderer with an interactive user interface, validating our approach and demonstrating its practicality and high efficiency with over 40 fps in scenes including both 3D Gaussians and mesh. Furthermore, our work highlights the potential of 3D Gaussians in real-time applications with dynamic lighting, offering insights into performance and optimization.

Jierui Ren, Haojie Jin, Bo Pang et al.

Modeling of high-frequency outgoing radiance distributions has long been a key challenge in rendering, particularly for glossy material. Such distributions concentrate radiative energy within a narrow lobe and are highly sensitive to changes in view direction. However, existing neural radiosity methods, which primarily rely on positional feature encoding, exhibit notable limitations in capturing these high-frequency, strongly view-dependent radiance distributions. To address this, we propose a highly-efficient approach by reflectance-aware ray cone encoding based on the neural radiosity framework, named neural cone radiosity. The core idea is to employ a pre-filtered multi-resolution hash grid to accurately approximate the glossy BSDF lobe, embedding view-dependent reflectance characteristics directly into the encoding process through continuous spatial aggregation. Our design not only significantly improves the network's ability to model high-frequency reflection distributions but also effectively handles surfaces with a wide range of glossiness levels, from highly glossy to low-gloss finishes. Meanwhile, our method reduces the network's burden in fitting complex radiance distributions, allowing the overall architecture to remain compact and efficient. Comprehensive experimental results demonstrate that our method consistently produces high-quality, noise-free renderings in real time under various glossiness conditions, and delivers superior fidelity and realism compared to baseline approaches.

Meng Gai, Guoping Wang, Sheng Li

Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.

Dongdong Meng, Sheng Li, Hao Wu et al.

Accurate automatic medical image segmentation relies on high-quality, dense annotations, which are costly and time-consuming. Weakly supervised learning provides a more efficient alternative by leveraging sparse and coarse annotations instead of dense, precise ones. However, segmentation performance degradation and overfitting caused by sparse annotations remain key challenges. To address these issues, we propose CmFNet, a novel 3D weakly supervised cross-modal medical image segmentation approach. CmFNet consists of three main components: a modality-specific feature learning network, a cross-modal feature learning network, and a hybrid-supervised learning strategy. Specifically, the modality-specific feature learning network and the cross-modal feature learning network effectively integrate complementary information from multi-modal images, enhancing shared features across modalities to improve segmentation performance. Additionally, the hybrid-supervised learning strategy guides segmentation through scribble supervision, intra-modal regularization, and inter-modal consistency, modeling spatial and contextual relationships while promoting feature alignment. Our approach effectively mitigates overfitting, delivering robust segmentation results. It excels in segmenting both challenging small tumor regions and common anatomical structures. Extensive experiments on a clinical cross-modal nasopharyngeal carcinoma (NPC) dataset (including CT and MR imaging) and the publicly available CT Whole Abdominal Organ dataset (WORD) show that our approach outperforms state-of-the-art weakly supervised methods. In addition, our approach also outperforms fully supervised methods when full annotation is used. Our approach can facilitate clinical therapy and benefit various specialists, including physicists, radiologists, pathologists, and oncologists.

Dongdong Meng, Sheng Li, Hao Wu et al.

Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve the accuracy of medical image segmentation by providing complementary information. However, they face challenges in achieving significant improvements under semi-supervised conditions due to the challenge of effectively leveraging unlabeled data. There is a significant need to create an effective and reliable multi-modal learning strategy for leveraging unlabeled data in semi-supervised segmentation. To address these issues, we propose a novel semi-supervised multi-modal medical image segmentation approach, which leverages complementary multi-modal information to enhance performance with limited labeled data. Our approach employs a multi-stage multi-modal fusion and enhancement strategy to fully utilize complementary multi-modal information, while reducing feature discrepancies and enhancing feature sharing and alignment. Furthermore, we effectively introduce contrastive mutual learning to constrain prediction consistency across modalities, thereby facilitating the robustness of segmentation results in semi-supervised tasks. Experimental results on two multi-modal datasets demonstrate the superior performance and robustness of the proposed framework, establishing its valuable potential for solving medical image segmentation tasks in complex scenarios.

Mai Su, Zhongtao Wang, Huishan Au et al.

3DGS is an emerging and increasingly popular technology in the field of novel view synthesis. Its highly realistic rendering quality and real-time rendering capabilities make it promising for various applications. However, when applied to large-scale aerial urban scenes, 3DGS methods suffer from issues such as excessive memory consumption, slow training times, prolonged partitioning processes, and significant degradation in rendering quality due to the increased data volume. To tackle these challenges, we introduce \textbf{HUG}, a novel approach that enhances data partitioning and reconstruction quality by leveraging a hierarchical neural Gaussian representation. We first propose a visibility-based data partitioning method that is simple yet highly efficient, significantly outperforming existing methods in speed. Then, we introduce a novel hierarchical weighted training approach, combined with other optimization strategies, to substantially improve reconstruction quality. Our method achieves state-of-the-art results on one synthetic dataset and four real-world datasets.

Xiao Zhang, Lu Zou, Tao Lu et al.

Category-level object pose estimation aims to predict the 6D pose and size of previously unseen instances from predefined categories, requiring strong generalization across diverse object instances. Although many previous methods attempt to mitigate intra-class variations, they often struggle with instances exhibiting complex geometries or significant deviations from canonical shapes. To address this issue, we propose INKL-Pose, a novel category-level object pose estimation framework that enables INstance-adaptive Keypoint Learning with local-to-global geometric aggregation. Specifically, our method first predicts semantically consistent and geometrically informative keypoints using an Instance-Adaptive Keypoint Detector, then refines them: (1) a Local Keypoint Feature Aggregator capturing fine-grained geometries, and (2) a Global Keypoint Feature Aggregator using bidirectional Mamba for structural consistency. To enable bidirectional modeling in Mamba, we introduce a simple yet effective Feature Sequence Flipping strategy that preserves spatial coherence while constructing backward feature sequence. Additionally, we design a surface loss and a separation loss to encourage uniform coverage and spatial diversity in keypoint distribution. The resulting keypoints are mapped to a canonical space for 6D pose and size regression. Extensive experiments on CAMERA25, REAL275, and HouseCat6D show that INKL-Pose achieves state-of-the-art performance with 16.7M parameters and runs at 36 FPS on an NVIDIA RTX 4090D GPU.

Lu Zou, Zhangjin Huang, Naijie Gu et al.

This paper presents 6D-ViT, a transformer-based instance representation learning network, which is suitable for highly accurate category-level object pose estimation on RGB-D images. Specifically, a novel two-stream encoder-decoder framework is dedicated to exploring complex and powerful instance representations from RGB images, point clouds and categorical shape priors. For this purpose, the whole framework consists of two main branches, named Pixelformer and Pointformer. The Pixelformer contains a pyramid transformer encoder with an all-MLP decoder to extract pixelwise appearance representations from RGB images, while the Pointformer relies on a cascaded transformer encoder and an all-MLP decoder to acquire the pointwise geometric characteristics from point clouds. Then, dense instance representations (i.e., correspondence matrix, deformation field) are obtained from a multi-source aggregation network with shape priors, appearance and geometric information as input. Finally, the instance 6D pose is computed by leveraging the correspondence among dense representations, shape priors, and the instance point clouds. Extensive experiments on both synthetic and real-world datasets demonstrate that the proposed 3D instance representation learning framework achieves state-of-the-art performance on both datasets, and significantly outperforms all existing methods.

Xutong Jin, Sheng Li, Guoping Wang et al.

We present a novel learning-based modal sound synthesis approach that includes a mixed vibration solver for modal analysis and an end-to-end sound radiation network for acoustic transfer. Our mixed vibration solver consists of a 3D sparse convolution network and a Locally Optimal Block Preconditioned Conjugate Gradient module (LOBPCG) for iterative optimization. Moreover, we highlight the correlation between a standard modal vibration solver and our network architecture. Our radiation network predicts the Far-Field Acoustic Transfer maps (FFAT Maps) from the surface vibration of the object. The overall running time of our learning method for any new object is less than one second on a GTX 3080 Ti GPU while maintaining a high sound quality close to the ground truth that is computed using standard numerical methods. We also evaluate the numerical accuracy and perceptual accuracy of our sound synthesis approach on different objects corresponding to various materials.

Qingtian Zhu, Chen Min, Zizhuang Wei et al.

3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality. As a dominant technique in artificial intelligence, deep learning has been successfully adopted to solve various computer vision problems. However, deep learning for 3D reconstruction is still at its infancy due to its unique challenges and varying pipelines. To stimulate future research, this paper presents a review of recent progress in deep learning methods for Multi-view Stereo (MVS), which is considered as a crucial task of image-based 3D reconstruction. It also presents comparative results on several publicly available datasets, with insightful observations and inspiring future research directions.

Hongwei Yi, Shaoshuai Shi, Mingyu Ding et al.

3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles. Second, the distribution of point cloud on vehicles varies continuously with increasing depths, which may not be well modeled by a single model. In this work, we propose a unified model SegVoxelNet to address the above two problems. A semantic context encoder is proposed to leverage the free-of-charge semantic segmentation masks in the bird's eye view. Suspicious regions could be highlighted while noisy regions are suppressed by this module. To better deal with vehicles at different depths, a novel depth-aware head is designed to explicitly model the distribution differences and each part of the depth-aware head is made to focus on its own target detection range. Extensive experiments on the KITTI dataset show that the proposed method outperforms the state-of-the-art alternatives in both accuracy and efficiency with point cloud as input only.

Yu Chen, Yisong Chen, Guoping Wang

3D reconstruction has been developing all these two decades, from moderate to medium size and to large scale. It's well known that bundle adjustment plays an important role in 3D reconstruction, mainly in Structure from Motion(SfM) and Simultaneously Localization and Mapping(SLAM). While bundle adjustment optimizes camera parameters and 3D points as a non-negligible final step, it suffers from memory and efficiency requirements in very large scale reconstruction. In this paper, we study the development of bundle adjustment elaborately in both conventional and distributed approaches. The detailed derivation and pseudo code are also given in this paper.

Wei Li, Chengwei Pan, Rong Zhang et al.

Simulation systems have become an essential component in the development and validation of autonomous driving technologies. The prevailing state-of-the-art approach for simulation is to use game engines or high-fidelity computer graphics (CG) models to create driving scenarios. However, creating CG models and vehicle movements (e.g., the assets for simulation) remains a manual task that can be costly and time-consuming. In addition, the fidelity of CG images still lacks the richness and authenticity of real-world images and using these images for training leads to degraded performance. In this paper we present a novel approach to address these issues: Augmented Autonomous Driving Simulation (AADS). Our formulation augments real-world pictures with a simulated traffic flow to create photo-realistic simulation images and renderings. More specifically, we use LiDAR and cameras to scan street scenes. From the acquired trajectory data, we generate highly plausible traffic flows for cars and pedestrians and compose them into the background. The composite images can be re-synthesized with different viewpoints and sensor models. The resulting images are photo-realistic, fully annotated, and ready for end-to-end training and testing of autonomous driving systems from perception to planning. We explain our system design and validate our algorithms with a number of autonomous driving tasks from detection to segmentation and predictions. Compared to traditional approaches, our method offers unmatched scalability and realism. Scalability is particularly important for AD simulation and we believe the complexity and diversity of the real world cannot be realistically captured in a virtual environment. Our augmented approach combines the flexibility in a virtual environment (e.g., vehicle movements) with the richness of the real world to allow effective simulation of anywhere on earth.

Longfei Liu, Sheng Li, Yisong Chen et al.

Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing. We present a new method, called X-GANs, for reconstruction of arbitrary corrupted resource based on a variant of conditional generative adversarial networks (conditional GANs). In our method, a novel generator and multi-scale discriminators are proposed, as well as the combined adversarial losses, which integrate a VGG perceptual loss, an adversarial perceptual loss, and an elaborate corresponding point loss together based on the analysis of image feature. Our conditional GANs have enabled a variety of applications in image reconstruction, including image denoising, image restoration from quite a sparse sampling, image inpainting, image recovery from the severely polluted block or even color-noise dominated images, which are extreme cases and haven't been addressed in the status quo. We have significantly improved the accuracy and quality of image reconstruction. Extensive perceptual experiments on datasets ranging from human faces to natural scenes demonstrate that images reconstructed by the presented approach are considerably more realistic than alternative work. Our method can also be extended to handle high-ratio image compression.