[PDF] Multi-view Scene Flow Estimation: A View Centered Variational Approach | Semantic Scholar (2024)

This work proposes to represent the dynamic scene as a collection of rigidly moving planes, into which the input images are segmented, and shows that such a view-consistent multi-frame scheme significantly improves accuracy, especially in the presence of occlusions, and increases robustness against adverse imaging conditions.

It is shown that such a view-consistent multi-frame scheme greatly improves scene flow computation in the presence of occlusions, and increases its robustness against adverse imaging conditions, such as specularities.

A continuous optimization method for solving dense 3D scene flow problems from stereo imagery using a fine superpixel segmentation that is fixed a-priori and a factor graph formulation that decomposes the problem into photometric, geometric, and smoothing constraints is proposed.

A monocular camera scene flow estimation algorithm that can use three sequential frames at least to get scene flow in world coordinate, without optical flow or disparity inputting is proposed.

A unified framework is proposed for estimating a 3D motion field using multiple cameras that can handle both arbitrary large motions and sub-pixel displacements and takes advantage of the geometric information provided by the depth camera to define a surface domain over which photometric constraints can be consistently integrated in 3D.

A novel model that represents the dynamic 3D scene by a collection of planar, rigidly moving, local segments is introduced that achieves leading performance levels, exceeding competing3D scene flow methods, and even yielding better 2D motion estimates than all tested dedicated optical flow techniques.

The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimated intensity value and a confidence measure of this value.

A novel variational model to jointly estimate geometry and motion from a sequence of light fields captured with a plenoptic camera is presented, which enforces multi-view geometry consistency, and piecewise smoothness assumptions on the scene flow variables.

This work proposes a method that uses a monocular sequence for joint direct estimation of dense scene flow and relative depth, analogous to the classical Horn and Schunck optical flow estimation although it involves 3D motion and depth rather than 2D image motion.

This work introduces a framework to estimate and refine 3D scene flow which connects 3D structures of a scene across different frames and improves the reconstructed 3D model from the refined 3D point cloud in real-world dataset.

...

...

This paper proposes to recover the scene flow by coupling the optical flow estimation in both cameras with dense stereo matching between the images, thus reducing the number of unknowns per image point.

A new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences that minimizes the prediction error of the shape and motion estimates and results in a simpler, more flexible, and more efficient implementation than in existing methods.

A novel system which integrates 3D scene flow and structure recovery in order to complement each other's performance, and does not assume rigidity of the scene motion, thus allowing for non-rigid motion in the scene.

An image-based photo-consistency score is proposed which can be efficiently computed and which fully handles projective distortion and partial occlusions and is demonstrated the effectiveness of the method on several challenging real-world dynamic scenes.

A variational framework for the estimation of stereoscopic scene flow, i.e., the motion of points in the three-dimensional world from stereo image sequences, which partially decouple the depth estimation from the motion estimation, which has many practical advantages.

A PDE-based explicit scheme for moving iteratively towards the solution has been developed and the Tikhonov quadratic regularization term usually used to recover smooth solution is replaced by a function of the gradient depth specifically derived to allow depth discontinuities formation in the solution.

It is shown that complete surfel-based reconstructions can be created by repeatedly applying an algorithm called Surfel Sampling that combines sampling and parameter estimation to fit a single surfel to a small, bounded region of space-time.

Novel hard constraints are introduced in this paper to make the algorithms more accurate and robust and to see promising experimental results by applying the algorithms to real imagery.

This paper shows that inference with triple cliques can be effectively optimized, and demonstrates the usefulness of the second-order prior and the efficacy of the optimization framework.

...

...