A Trajectory-Driven Spatio-Temporal Refinement Solution for CVPR 2026 8th UG2+ Challenge Track 3: DOST

• URL: http://arxiv.org/abs/2606.00522v2
• Date: Thu, 04 Jun 2026 10:14:10 GMT
• Title: A Trajectory-Driven Spatio-Temporal Refinement Solution for CVPR 2026 8th UG2+ Challenge Track 3: DOST
• Abstract summary: We present our solution for the 8th UG2+ Challenge (CVPR 2026) Track 3: Dynamic Object in Turbulence (DOST).<n>Our method is built upon the strong baseline framework Segment Any Motion (SegAnyMo), which provides powerful mask generation and motion tracking capabilities.
• Score: 4.253597037211198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we present our solution for the 8th UG2+ Challenge (CVPR 2026) Track 3: Dynamic Object Segmentation in Turbulence (DOST). Our method is built upon the strong baseline framework Segment Any Motion (SegAnyMo), which provides powerful mask generation and motion tracking capabilities. To further boost the segmentation performance under severe atmospheric distortions, we propose two key improvements. First, we employ a data-centric domain adaptation strategy. We significantly expand our training data by incorporating selected sequences from the DAVIS dataset alongside a subset of the DOST dataset, and apply simulated atmospheric fluctuation degradations to enhance the model's robustness against complex geometric distortions. Second, we introduce a spatio-temporal post-processing module. This refinement step effectively removes persistent boundary-connected false foregrounds and short-lived fragmented noise, while strictly preserving genuine small targets and maintaining original individual labels across frames. With these combined strategies, our proposed method ranks the 2st place in the challenge.

Related papers

• Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation [53.60856261088647]
  This paper proposes to shift the condensation paradigm from optimization-based inversion to deterministic latent mapping.<n>We represent action segments as continuous trajectories anchored by sparse latent points in the noise manifold.<n>Our framework significantly outperforms state-of-the-art methods in segmentation performance across common datasets.
  arXiv  Detail & Related papers  (2026-07-10T04:00:26Z)
• Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement [18.250105847259285]
  This report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object in Turbulence (DOST)<n>We design a training-free multi-signal segmentation pipeline that combines pretrained motion estimation, self-supervised semantic priors, background anomaly modeling, manually calibrated proposal fusion, and SAM2-based mask refinement.<n>This design is suitable for the DOST setting, where severe atmospheric turbulence produces pseudo-motion, blur, and intermittent target visibility, making a single motion cue unreliable.
  arXiv  Detail & Related papers  (2026-05-28T03:18:18Z)
• X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge [1.353422102543835]
  We present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions.<n>Our method is built upon the strong baseline framework X-Restormer, which effectively captures both channel-wise global dependencies and spatially-local structural information.<n>With these strategies, our proposed method successfully ranks the 1st place in the challenge.
  arXiv  Detail & Related papers  (2026-05-13T09:41:09Z)
• Dual-End Consistency Model [41.982957134224904]
  Slow iterative sampling is a major bottleneck for the practical deployment of diffusion and flow-based generative models.<n>We propose a Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training.<n>Our method achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches.
  arXiv  Detail & Related papers  (2026-02-11T11:51:01Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• MASSeg : 2nd Technical Report for 4th PVUW MOSE Track [4.988774092444048]
  We propose an improved model named MASSeg for complex video object segmentation, and construct an enhanced dataset, MOSE+.<n>During training, we incorporate a combination of inter-frame consistent and inconsistent data augmentation strategies to improve robustness and generalization.<n> MASSeg achieves a J score of 0.8250, F score of 0.9007, and a J&F score of 0.8628 on the MOSE test set.
  arXiv  Detail & Related papers  (2025-04-14T14:15:46Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
  We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.<n>We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling.<n>We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T08:23:38Z)
• Dynamic Position Transformation and Boundary Refinement Network for Left Atrial Segmentation [17.09918110723713]
  Left atrial (LA) segmentation is a crucial technique for irregular heartbeat (i.e., atrial fibrillation) diagnosis. Most current methods for LA segmentation strictly assume that the input data is acquired using object-oriented center cropping. We propose a novel Dynamic Position transformation and Boundary refinement Network (DPBNet) to tackle these issues.
  arXiv  Detail & Related papers  (2024-07-07T22:09:35Z)
• Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking [2.487142846438629]
  3 single object tracking within LIDAR point is pivotal task in computer vision. Existing methods, which depend solely on appearance matching via networks or utilize information from successive frames, encounter significant challenges. We design an innovative cross-frame bi-temporal motion tracker, named STMD-Tracker, to mitigate these challenges.
  arXiv  Detail & Related papers  (2024-03-23T13:15:44Z)
• Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence [10.8380383565446]
  We present an unsupervised approach for segmenting moving objects in videos downgraded by atmospheric turbulence. We first identify a small set of moving object pixels with high confidence, then gradually grow a foreground mask from those seeds to segment all moving objects. Results show that our method achieves good accuracy in segmenting moving objects and is robust for long-range videos with various turbulence strengths.
  arXiv  Detail & Related papers  (2023-11-06T22:17:18Z)
• Leveraging the Power of Data Augmentation for Transformer-based Tracking [64.46371987827312]
  We propose two data augmentation methods customized for tracking. First, we optimize existing random cropping via a dynamic search radius mechanism and simulation for boundary samples. Second, we propose a token-level feature mixing augmentation strategy, which enables the model against challenges like background interference.
  arXiv  Detail & Related papers  (2023-09-15T09:18:54Z)
• DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions [52.63323657077447]
  We propose DNMOT, an end-to-end trainable DeNoising Transformer for multiple object tracking. Specifically, we augment the trajectory with noises during training and make our model learn the denoising process in an encoder-decoder architecture. We conduct extensive experiments on the MOT17, MOT20, and DanceTrack datasets, and the experimental results show that our method outperforms previous state-of-the-art methods by a clear margin.
  arXiv  Detail & Related papers  (2023-09-09T04:40:01Z)
• Learning to Segment Rigid Motions from Two Frames [72.14906744113125]
  We propose a modular network, motivated by a geometric analysis of what independent object motions can be recovered from an egomotion field. It takes two consecutive frames as input and predicts segmentation masks for the background and multiple rigidly moving objects, which are then parameterized by 3D rigid transformations. Our method achieves state-of-the-art performance for rigid motion segmentation on KITTI and Sintel.
  arXiv  Detail & Related papers  (2021-01-11T04:20:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.