Seamless integration of both aerial and street view images remains a significant challenge in neural scene reconstruction and rendering. Existing methods predominantly focus on single domain, limiting their applications in immersive environments, which demand extensive free view exploration with large view changes both horizontally and vertically. We introduce Horizon-Gs, a novel approach built upon Gaussian Splatting techniques, tackles the unified reconstruction and rendering for aerial and street views. Our method addresses the key challenges of combining these perspectives with a new training strategy, overcoming viewpoint discrepancies to generate high-fidelity scenes. We also curate a high-quality aerial-to-ground views dataset encompassing both synthetic and real-world scene to advance further research. Experiments across diverse urban scene datasets confirm the effectiveness of our method.

We introduce AnySplat, a feed-forward network for novel-view synthesis from uncalibrated image collections. In contrast to traditional neural-rendering pipelines that demand known camera poses and per-scene optimization, or recent feed-forward methods that buckle under the computational weight of dense views—our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi-view datasets without any pose annotations. In extensive zero-shot evaluations, AnySplat matches the quality of pose-aware baselines in both sparse- and dense-view scenarios while surpassing existing pose-free approaches. Moreover, it greatly reduces rendering latency compared to optimization-based neural fields, bringing real-time novel-view synthesis within reach for unconstrained capture settings. Project page: https://city-super.github.io/anysplat/.

Recent advancements in neural rendering methods, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D-GS), have significantly revolutionized photo-realistic novel view synthesis of scenes with multiple photos or videos as input. However, existing approaches within the NeRF and 3D-GS frameworks often assume the independence of point sampling and ray casting, which are intrinsic to volume rendering and alpha-blending techniques. These underlying assumptions limit the ability to aggregate context within subspaces, such as densities and colors in the radiance fields and pixels on the image plane, leading to synthesized images that lack fine details and smoothness. To overcome this, we propose a universal framework, MixRF, comprising a Radiance Field Mixer (RF-mixer) and a Color Domain Mixer (CD-mixer), to sufficiently aggregate and fully explore information in neighboring sampled points and casting rays, separately. The RF-mixer treats sampled points as an explicit point cloud, enabling the aggregation of density and color attributes from neighboring points to better capture local geometry and appearance. Meanwhile, the CD-mixer rearranges rendered pixels on the sub-image plane, improving smoothness and recovering fine details and textures. Both mixers employ a kernel-based mixing strategy to facilitate effective and controllable attribute aggregation, ensuring a more comprehensive exploration of radiance values and pixel information. Extensive experiments demonstrate that our MixRF framework is compatible with radiance field-based methods, including NeRF and 3D-GS designs. The proposed framework dramatically enhances performance in both qualitative and quantitative evaluations, with less than a $ 25\%$25% increase in computational overhead during inference.

Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications. The recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed combining the benefits of both primitive-based representations and volumetric representations. However, it often leads to heavily redundant Gaussians that try to fit every training view, neglecting the underlying scene ge-ometry. Consequently, the resulting model becomes less robust to significant view changes, texture-less area and lighting effects. We introduce Scaffold-GS, which uses an-chor points to distribute local 3D Gaussians, and predicts their attributes on-the-fly based on viewing direction and distance within the view frustum. Anchor growing and pruning strategies are developed based on the importance of neural Gaussians to reliably improve the scene cover-age. We show that our method effectively reduces redun-dant Gaussians while delivering high-quality rendering. We also demonstrates an enhanced capability to accommodate scenes with varying levels-of-detail and view-dependent ob-servations, without sacrificing the rendering speed. Project page: https://city-super.github.iolscaffold-gsl.

Representing 3D scenes from multiview images remains a core challenge in computer vision and graphics, requiring both reliable rendering and reconstruction, which often conflicts due to the mismatched prioritization of image quality over precise underlying scene geometry. Although both neural implicit surfaces and explicit Gaussian primitives have advanced with neural rendering techniques, current methods impose strict constraints on density fields or primitive shapes, which enhances the affinity for geometric reconstruction at the sacrifice of rendering quality. To address this dilemma, we introduce GSDF, a dual-branch architecture combining 3D Gaussian Splatting (3DGS) and neural Signed Distance Fields (SDF). Our approach leverages mutual guidance and joint supervision during the training process to mutually enhance reconstruction and rendering. Specifically, our method guides the Gaussian primitives to locate near potential surfaces and accelerates the SDF convergence. This implicit mutual guidance ensures robustness and accuracy in both synthetic and real-world scenarios. Experimental results demonstrate that our method boosts the SDF optimization process to reconstruct more detailed geometry, while reducing floaters and blurry edge artifacts in rendering by aligning Gaussian primitives with the underlying geometry.

In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an "early-fusion" or "late-fusion" manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarity. To address the problem, we propose a novel end-to-end framework, which consists of 2D and 3D branches with multiple bidirectional fusion connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to extract the LiDAR features, as it preserves the geometric structure of point clouds. To fuse dense image features and sparse point features, we propose a learnable operator named bidirectional camera-LiDAR fusion module (Bi-CLFM). We instantiate two types of the bidirectional fusion pipeline, one based on the pyramidal coarse-to-fine architecture (dubbed CamLiPWC), and the other one based on the recurrent all-pairs field transforms (dubbed CamLiRAFT). On FlyingThings3D, both CamLiPWC and CamLiRAFT surpass all existing methods and achieve up to a 47.9% reduction in 3D end-point-error from the best published result. Our best-performing model, CamLiRAFT, achieves an error of 4.26% on the KITTI Scene Flow benchmark, ranking 1st among all submissions with much fewer parameters. Besides, our methods have strong generalization performance and the ability to handle non-rigid motion.

Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from data scarcity and sparsity. Previous work has taken the first step to scale up the kernel size from 3 × 3 × 3 to 7 × 7 × 7 by introducing block-shared weights. However, to reduce the feature variations within a block, it only employs modest block size and fails to achieve larger kernels like the 21 × 21 × 21. To address this issue, we propose a new method, called LinK, to achieve a wider-range perception receptive field in a convolution-like manner with two core designs. The first is to replace the static kernel matrix with a linear kernel generator, which adaptively provides weights only for non-empty voxels. The second is to reuse the pre-computed aggregation results in the overlapped blocks to reduce computation complexity. The proposed method successfully enables each voxel to perceive context within a range of 21 × 21 × 21. Extensive experiments on two basic perception tasks, 3D object detection and 3D semantic segmentation, demonstrate the effectiveness of our method. Notably, we rank 1st on the public leaderboard of the 3D detection benchmark of nuScenes (LiDAR track), by simply incorporating a LinK-based backbone into the basic detector, CenterPoint. We also boost the strong segmentation baseline's mIoU with 2.7% in the SemanticKITTI test set. Code is available at https://github.com/MCG-NJU/LinK.

Camera-based 3D object detection in BEV (Bird’s Eye View) space has drawn great attention over the past few years. Dense detectors typically follow a two-stage pipeline by first constructing a dense BEV feature and then performing object detection in BEV space, which suffers from complex view transformations and high computation cost. On the other side, sparse detectors follow a query-based paradigm without explicit dense BEV feature construction, but achieve worse performance than the dense counterparts. In this paper, we find that the key to mitigate this performance gap is the adaptability of the detector in both BEV and image space. To achieve this goal, we propose SparseBEV, a fully sparse 3D object detector that outperforms the dense counterparts. SparseBEV contains three key designs, which are (1) scale-adaptive self attention to aggregate features with adaptive receptive field in BEV space, (2) adaptive spatio-temporal sampling to generate sampling locations under the guidance of queries, and (3) adaptive mixing to decode the sampled features with dynamic weights from the queries. On the test split of nuScenes, SparseBEV achieves the state-of-the-art performance of 67.5 NDS. On the val split, SparseBEV achieves 55.8 NDS while maintaining a real-time inference speed of 23.5 FPS. Code is available at https://github.com/MCG-NJU/SparseBEV.

Aggregating neighbor features is essential for point cloud neural network. In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently. Thus, each point has to participate in the calculation repeatedly, generating redundant duplicates in the memory, leading to intensive computation costs and memory consumption. Meanwhile, to pursue higher accuracy, previous methods often rely on a complex local aggregator to extract fine geometric representation, further slowing down the processing pipeline. To address these issues, we propose a new local aggregator of linear complexity for point cloud analysis, coined as APP. Specifically, we introduce an auxiliary container as an anchor to exchange features between the source point and the aggregating center. Each source point pushes its feature to only one auxiliary container, and each center point pulls features from only one auxiliary container. This avoids the re-computation issue of each source point. To facilitate the learning of the local structure of point cloud, we use an online normal estimation module to provide explainable geometric information to enhance our APP modeling capability. Our built network is more efficient than all the previous baselines with a clear margin while still consuming a lower memory. Experiments on classification and semantic segmentation demonstrate that APP-Net reaches comparable accuracies to other networks. In the classification task, it can process more than 10,000 samples per second with less than 10GB of memory on a single GPU. We will release the code at https://github.com/MCG-NJU/ APP-Net.

In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an “early-fusion“ or “late-fusion“ manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarity. To address the problem, we propose a novel end-to-end framework, called CamLiFlow. It consists of 2D and 3D branches with multiple bidirectional connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to better extract the geometric features and design a symmetric learnable operator to fuse dense image features and sparse point features. Experiments show that CamLiFlow achieves better performance with fewer parameters. Our method ranks 1st on the KITTI Scene Flow benchmark, outperforming the previous art with 1/7 parameters. Code is available at https://github.com/MCG-NJU/CamLiFlow.

Previous point cloud semantic segmentation networks use the same process to aggregate features from neighbors of the same category and different categories. However, the joint area between two objects usually only occupies a small percentage in the whole scene. Thus the networks are well- trained for aggregating features from the same category point while not fully trained on aggregating points of different categories. To address this issue, this paper proposes to utilize different aggregation strategies between the same category and different categories. Specifically, it presents a customized module, termed as Category Guided Aggregation (CGA), where it first identifies whether the neighbors belong to the same category with the center point or not, and then handles the two types of neighbors with two carefully-designed modules. Our CGA presents a general network module and could be leveraged in any existing semantic segmentation network. Experiments on three different backbones demonstrate the effectiveness of our method.