Related papers: Let-It-Flow: Simultaneous Optimization of 3D Flow …

Clustering points in a vector space or nodes in a graph is a ubiquitous primitive in statistical data analysis, and it is commonly used for exploratory data analysis. In practice, it is often of interest to "refine" or "improve" a given…

Scene flow, which provides the 3D motion field of the first frame from two consecutive point clouds, is vital for dynamic scene perception. However, contemporary scene flow methods face three major challenges. Firstly, they lack global flow…

Accurate 3D scene flow estimation is critical for autonomous systems to navigate dynamic environments safely, but creating the necessary large-scale, manually annotated datasets remains a significant bottleneck for developing robust…

Tracking motions of humans or objects in the surroundings of the robot is essential to improve safe robot motions and reactions. In this work, we present an approach for scene flow estimation from low-density and noisy point clouds acquired…

Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D…

Visual feature clustering is one of the cost-effective approaches to segment objects in videos. However, the assumptions made for developing the existing algorithms prevent them from being used in situations like segmenting an unknown…

Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create…

Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically…

We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a…

Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders…

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…

The proposed RMS-FlowNet++ is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation that can operate on high-density point clouds. For hierarchical scene f low estimation, existing methods rely on…

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep…

Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a…

We present a framework to use recently introduced Capsule Networks for solving the problem of Optical Flow, one of the fundamental computer vision tasks. Most of the existing state of the art deep architectures either uses a correlation…

Diffusion models are a powerful framework for tackling ill-posed problems, with recent advancements extending their use to point cloud upsampling. Despite their potential, existing diffusion models struggle with inefficiencies as they map…

Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers…

The test-time optimization of scene flow - using a coordinate network as a neural prior - has gained popularity due to its simplicity, lack of dataset bias, and state-of-the-art performance. We observe, however, that although coordinate…

We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suffer from incomplete scene initialization for dynamic…