From optical flow to dense long term correspondences

Crivelli, Tomas; Conze, Pierre-Henri; Robert, Philippe; Pérez, Patrick

doi:10.1109/icip.2012.6466795

Cited by 9 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Crivelli et al [6] proposed an automatic method for mapping textures between images. They use optical flow as a basic algorithm to find trajectories with space-time continuity over the frames of video.…”

Section: B Editing Textures In Video Sequencesmentioning

confidence: 99%

“…Because our algorithm only merges regions that have a smooth correspondence field together, after the algorithm is finished each region covered by a different B-Spline surface can be considered a different shared object. To test our algorithm against other methods, we performed a numerical comparison of our results with those of the Co-recognition work of Cho et al [9] and NRDC [1], shown in Table II [6], initial correspondences from NRDC [1], and the result of our Trivariate-Spline approximation. Errors in Crivelli et al's result are large, while the trajectory from NRDC is perhaps more accurate but very noisy (high variance).…”

Section: A Unsupervised Recognition and Segmentation Of Multiple Commentioning

confidence: 99%

See 1 more Smart Citation

A Surface Approximation Method for Image and Video Correspondences

Huang

Wang

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Although finding correspondences between similar images is an important problem in image processing, the existing algorithms cannot find accurate and dense correspondences in images with significant changes in lighting/transformation or with the non-rigid objects. This paper proposes a novel method for finding accurate and dense correspondences between images even in these difficult situations. Starting with the non-rigid dense correspondence algorithm [1] to generate an initial correspondence map, we propose a new geometric filter that uses cubic B-Spline surfaces to approximate the correspondence mapping functions for shared objects in both images, thereby eliminating outliers and noise. We then propose an iterative algorithm which enlarges the region containing valid correspondences. Compared with the existing methods, our method is more robust to significant changes in lighting, color, or viewpoint. Furthermore, we demonstrate how to extend our surface approximation method to video editing by first generating a reliable correspondence map between a given source frame and each frame of a video. The user can then edit the source frame, and the changes are automatically propagated through the entire video using the correspondence map. To evaluate our approach, we examine applications of unsupervised image recognition and video texture editing, and show that our algorithm produces better results than those from state-of-the-art approaches.

show abstract

Section: B Editing Textures In Video Sequencesmentioning

confidence: 99%

Section: A Unsupervised Recognition and Segmentation Of Multiple Commentioning

confidence: 99%

A Surface Approximation Method for Image and Video Correspondences

Huang

Wang

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…It links each pixel x a of I a to a corresponding position in I b . Elementary optical flow fields can be computed between consecutive frames or with different frame steps [11,12], i.e. with larger inter-frame distances.…”

Section: Combinatorial Multi-step Integrationmentioning

confidence: 99%

“…Following a similar approach to that presented in [10], one can select for each pixel the optimal motion vector among a set of candidate motion fields based on intrinsic motion field quality and spatial regularization. A more sophisticated processing, described in [11,12], consists in sequentially merging a set of concatenated multi-step motion fields at intermediate frames up to the target frame. However, in either case, the optimal motion vector selection strongly depends on the same optical flow assumptions that frequently fail between distant frames.…”

Section: Introductionmentioning

confidence: 99%

Dense motion estimation between distant frames: Combinatorial multi-step integration and statistical selection

Conze

Crivelli

Robert

et al. 2013

2013 IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

Accurate estimation of dense point correspondences between two distant frames of a video sequence is a challenging task. To address this problem, we present a combinatorial multistep integration procedure which allows one to obtain a large set of candidate motion fields between the two distant frames by considering multiple motion paths across the video sequence. Given this large candidate set, we propose to perform the optimal motion vector selection by combining a global optimization stage with a new statistical processing. Instead of considering a selection only based on intrinsic motion field quality and spatial regularization, the statistical processing exploits the spatial distribution of candidates and introduces an intra-candidate quality based on forward-backward consistency. Experiments evaluate the effectiveness of our method for distant motion estimation in the context of video editing.

show abstract

“…The alternative concept of multi-step flow (Crivelli et al, 2012b;Crivelli et al, 2012a) focuses on how to construct dense fields of correspondences over extended time periods using multi-step optical flows (optical flows computed between consecutive frames or with larger inter-frame distances). Multi-step flow sequentially merges a set of displacement fields at each intermediate frame, up to the target frame.…”

Section: Introductionmentioning

confidence: 99%

Dense Long-term Motion Estimation via Statistical Multi-step Flow

2014

Proceedings of the 9th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:We present statistical multi-step flow, a new approach for dense motion estimation in long video sequences. Towards this goal, we propose a two-step framework including an initial dense motion candidates generation and a new iterative motion refinement stage. The first step performs a combinatorial integration of elementary optical flows combined with a statistical candidate displacement fields selection and focuses especially on reducing motion inconsistency. In the second step, the initial estimates are iteratively refined considering several motion candidates including candidates obtained from neighboring frames. For this refinement task, we introduce a new energy formulation which relies on strong temporal smoothness constraints. Experiments compare the proposed statistical multi-step flow approach to state-of-the-art methods through both quantitative assessment using the Flag benchmark dataset and qualitative assessment in the context of video editing.

show abstract

From optical flow to dense long term correspondences

Abstract: Dense point matching and tracking in image sequences

Cited by 9 publications

References 10 publications

A Surface Approximation Method for Image and Video Correspondences

A Surface Approximation Method for Image and Video Correspondences

Dense motion estimation between distant frames: Combinatorial multi-step integration and statistical selection

Dense Long-term Motion Estimation via Statistical Multi-step Flow

Contact Info

Product

Resources

About