Related papers: Neural Eulerian Scene Flow Fields

6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues…

Scene flow estimation, which extracts point-wise motion between scenes, is becoming a crucial task in many computer vision tasks. However, all of the existing estimation methods utilize only the unidirectional features, restricting the…

Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to approximate…

LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera sensors, they often…

3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow.…

Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimates dense motion but breaks down on articulated bodies, where pixel-level supervision is…

Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance measured by average End-Point Error (EPE) has improved over…

Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel…

In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of…

Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point…

Current scene flow methods broadly fail to describe motion on small objects, and current scene flow evaluation protocols hide this failure by averaging over many points, with most drawn larger objects. To fix this evaluation failure, we…

In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particularly for generic obstacles/objects, due to appearance and…

Event cameras respond to scene dynamics and offer advantages to estimate motion. Following recent image-based deep-learning achievements, optical flow estimation methods for event cameras have rushed to combine those image-based methods…

Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement…

We propose a method for the data-driven inference of temporal evolutions of physical functions with deep learning. More specifically, we target fluid flows, i.e. Navier-Stokes problems, and we propose a novel LSTM-based approach to predict…

Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques largely focus on addressing the cross-image matching with…

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…

Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving…

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that…

We present a self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth to learn optical flow for hallucinated occlusions. We…