Recently, state space model (SSM) has gained great attention due to its promising performance, linear complexity, and long sequence modeling ability in both language and image domains. However, it is non-trivial to extend SSM to the point cloud field, because of the causality requirement of SSM and the disorder and irregularity nature of point clouds. In this paper, we propose a novel SSM-based point cloud processing backbone, named Point Mamba, with a causality-aware ordering mechanism. To construct the causal dependency relationship, we design an octree-based ordering strategy on raw irregular points, globally sorting points in a z-order sequence and also retaining their spatial proximity. Our method achieves state-of-the-art performance compared with transformer-based counterparts, with 93.4% accuracy and 75.7 mIOU respectively on the ModelNet40 classification dataset and ScanNet semantic segmentation dataset. Furthermore, our Point Mamba has linear complexity, which is more efficient than transformer-based methods. Our method demonstrates the great potential that SSM can serve as a generic backbone in point cloud understanding. Codes are released at https://github.com/IRMVLab/Point-Mamba.
NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by innovatively utilizing NeRF to enhance representation learning. Despite its notable performance, we uncover three decisive shortcomings in its current design, including semantic ambiguity, inappropriate sampling, and insufficient utilization of depth supervision. To combat the aforementioned problems, we present three corresponding solutions: 1) Semantic Enhancement. We project the freely available 3D segmentation annotations onto the 2D plane and leverage the corresponding 2D semantic maps as the supervision signal, significantly enhancing the semantic awareness of multi-view detectors. 2) Perspective-aware Sampling. Instead of employing the uniform sampling strategy, we put forward the perspective-aware sampling policy that samples densely near the camera while sparsely in the distance, more effectively collecting the valuable geometric clues. 3)Ordinal Residual Depth Supervision. As opposed to directly regressing the depth values that are difficult to optimize, we divide the depth range of each scene into a fixed number of ordinal bins and reformulate the depth prediction as the combination of the classification of depth bins as well as the regression of the residual depth values, thereby benefiting the depth learning process. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and ARKITScenes datasets. Notably, in ScanNetV2, NeRF-Det++ outperforms the competitive NeRF-Det by +1.9% in mAP@0.25 and +3.5% in mAP@0.50$. The code will be publicly at https://github.com/mrsempress/NeRF-Detplusplus.
In this study, we explore the influence of different observation spaces on robot learning, focusing on three predominant modalities: RGB, RGB-D, and point cloud. Through extensive experimentation on over 17 varied contact-rich manipulation tasks, conducted across two benchmarks and simulators, we have observed a notable trend: point cloud-based methods, even those with the simplest designs, frequently surpass their RGB and RGB-D counterparts in performance. This remains consistent in both scenarios: training from scratch and utilizing pretraining. Furthermore, our findings indicate that point cloud observations lead to improved policy zero-shot generalization in relation to various geometry and visual clues, including camera viewpoints, lighting conditions, noise levels and background appearance. The outcomes suggest that 3D point cloud is a valuable observation modality for intricate robotic tasks. We will open-source all our codes and checkpoints, hoping that our insights can help design more generalizable and robust robotic models.
Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained searching ranges, and struggle with accumulated inaccuracy arising from the coarse-to-fine structure. To alleviate these problems, we propose a novel uncertainty-aware scene flow estimation network (DifFlow3D) with the diffusion probabilistic model. Iterative diffusion-based refinement is designed to enhance the correlation robustness and resilience to challenging cases, e.g., dynamics, noisy inputs, repetitive patterns, etc. To restrain the generation diversity, three key flow-related features are leveraged as conditions in our diffusion model. Furthermore, we also develop an uncertainty estimation module within diffusion to evaluate the reliability of estimated scene flow. Our DifFlow3D achieves state-of-the-art performance, with 6.7\% and 19.1\% EPE3D reduction respectively on FlyingThings3D and KITTI 2015 datasets. Notably, our method achieves an unprecedented millimeter-level accuracy (0.0089m in EPE3D) on the KITTI dataset. Additionally, our diffusion-based refinement paradigm can be readily integrated as a plug-and-play module into existing scene flow networks, significantly increasing their estimation accuracy. Codes will be released later.
Feature matching is an essential step in visual localization, where the accuracy of camera pose is mainly determined by the established 2D-3D correspondence. Due to the noise, solving the camera pose accurately requires a sufficient number of well-distributed 2D-3D correspondences. Existing 2D-3D feature matching is typically achieved by finding the nearest neighbors in the feature space, and then removing the outliers by some hand-crafted heuristics. However, this may lead to a large number of potentially true matches being missed or the established correct matches being filtered out. In this work, we introduce a novel 2D-3D matching method, Geometry-Aided Matching (GAM), which uses both appearance information and geometric context to improve 2D-3D feature matching. GAM can greatly strengthen the recall of 2D-3D matches while maintaining high precision. We insert GAM into a hierarchical visual localization pipeline and show that GAM can effectively improve the robustness and accuracy of localization. Extensive experiments show that GAM can find more correct matches than hand-crafted heuristics and learning baselines. Our proposed localization method achieves state-of-the-art results on multiple visual localization datasets. Experiments on Cambridge Landmarks dataset show that our method outperforms the existing state-of-the-art methods and is six times faster than the top-performed method.
We present intrinsic neural radiance fields, dubbed IntrinsicNeRF, that introduce intrinsic decomposition into the NeRF-based~\cite{mildenhall2020nerf} neural rendering method and can perform editable novel view synthesis in room-scale scenes while existing inverse rendering combined with neural rendering methods~\cite{zhang2021physg, zhang2022modeling} can only work on object-specific scenes. Given that intrinsic decomposition is a fundamentally ambiguous and under-constrained inverse problem, we propose a novel distance-aware point sampling and adaptive reflectance iterative clustering optimization method that enables IntrinsicNeRF with traditional intrinsic decomposition constraints to be trained in an unsupervised manner, resulting in temporally consistent intrinsic decomposition results. To cope with the problem of different adjacent instances of similar reflectance in a scene being incorrectly clustered together, we further propose a hierarchical clustering method with coarse-to-fine optimization to obtain a fast hierarchical indexing representation. It enables compelling real-time augmented reality applications such as scene recoloring, material editing, and illumination variation. Extensive experiments on Blender Object and Replica Scene demonstrate that we can obtain high-quality, consistent intrinsic decomposition results and high-fidelity novel view synthesis even for challenging sequences. Code and data are available on the project webpage: https://zju3dv.github.io/intrinsic_nerf/.
We propose a novel end-to-end RGB-D SLAM, iDF-SLAM, which adopts a feature-based deep neural tracker as the front-end and a NeRF-style neural implicit mapper as the back-end. The neural implicit mapper is trained on-the-fly, while though the neural tracker is pretrained on the ScanNet dataset, it is also finetuned along with the training of the neural implicit mapper. Under such a design, our iDF-SLAM is capable of learning to use scene-specific features for camera tracking, thus enabling lifelong learning of the SLAM system. Both the training for the tracker and the mapper are self-supervised without introducing ground truth poses. We test the performance of our iDF-SLAM on the Replica and ScanNet datasets and compare the results to the two recent NeRF-based neural SLAM systems. The proposed iDF-SLAM demonstrates state-of-the-art results in terms of scene reconstruction and competitive performance in camera tracking.
We present a novel dual-flow representation of scene motion that decomposes the optical flow into a static flow field caused by the camera motion and another dynamic flow field caused by the objects' movements in the scene. Based on this representation, we present a dynamic SLAM, dubbed DeFlowSLAM, that exploits both static and dynamic pixels in the images to solve the camera poses, rather than simply using static background pixels as other dynamic SLAM systems do. We propose a dynamic update module to train our DeFlowSLAM in a self-supervised manner, where a dense bundle adjustment layer takes in estimated static flow fields and the weights controlled by the dynamic mask and outputs the residual of the optimized static flow fields, camera poses, and inverse depths. The static and dynamic flow fields are estimated by warping the current image to the neighboring images, and the optical flow can be obtained by summing the two fields. Extensive experiments demonstrate that DeFlowSLAM generalizes well to both static and dynamic scenes as it exhibits comparable performance to the state-of-the-art DROID-SLAM in static and less dynamic scenes while significantly outperforming DROID-SLAM in highly dynamic environments. Code and data are available on the project webpage: \urlstyle{tt} \textcolor{url_color}{\url{https://zju3dv.github.io/deflowslam/}}.
We present a novel panoptic visual odometry framework, termed PVO, to achieve a more comprehensive modeling of the scene's motion, geometry, and panoptic segmentation information. PVO models visual odometry (VO) and video panoptic segmentation (VPS) in a unified view, enabling the two tasks to facilitate each other. Specifically, we introduce a panoptic update module into the VO module, which operates on the image panoptic segmentation. This Panoptic-Enhanced VO module can trim the interference of dynamic objects in the camera pose estimation by adjusting the weights of optimized camera poses. On the other hand, the VO-Enhanced VPS module improves the segmentation accuracy by fusing the panoptic segmentation result of the current frame on the fly to the adjacent frames, using geometric information such as camera pose, depth, and optical flow obtained from the VO module. These two modules contribute to each other through a recurrent iterative optimization. Extensive experiments demonstrate that PVO outperforms state-of-the-art methods in both visual odometry and video panoptic segmentation tasks. Code and data are available on the project webpage: \urlstyle{tt} \textcolor{url_color}{\url{https://zju3dv.github.io/pvo/}}.