Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement

• URL: http://arxiv.org/abs/2605.29292v1
• Date: Thu, 28 May 2026 03:18:18 GMT
• Title: Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement
• Abstract summary: 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.
• Score: 18.250105847259285
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). 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. The method uses RAFT for dense motion responses, DINOv2 for semantic objectness priors, ViBe for training-free background modeling, and pretrained SAM2 for box-prompt mask refinement. Instead of optimizing an end-to-end segmentation network, our system operates entirely in inference mode. 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. The final submitted masks are evaluated by the official leaderboard, which reports 0.425041 mIoU and 0.457206 mDice. Since no task-specific model training or fine-tuning is performed, stronger learned temporal association, adaptive proposal selection, or task-specific adaptation may further improve the system.

Related papers

• AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis [0.2981315866322933]
  We present our system for the Multi-Task Learning track of the 11th Affective Behavior Analysis in-the-wild (ABAW) competition on s-Aff-Wild2.<n>The method focuses on post-encoder adaptation: frozen AffectNet-supervised backbones provide multi-resolution features.<n>For action-unit recognition, we adapt MAE-Face with Low-Rank Adaptation (LoRA) and use DISFA through per-unit expert routing.
  arXiv  Detail & Related papers  (2026-07-17T22:44:43Z)
• Native Video-Action Pretraining for Generalizable Robot Control [77.59831077077176]
  LingBot-VA 2.0 is a video-action foundation model built from the ground up for embodiment.<n>To meet the demands of high-frequency inference, our model employs a sparse MoE backbone.<n>Real-world deployment validates LingBot-VA 2.0 as a robust foundation model.
  arXiv  Detail & Related papers  (2026-07-09T16:15:43Z)
• A Trajectory-Driven Spatio-Temporal Refinement Solution for CVPR 2026 8th UG2+ Challenge Track 3: DOST [4.253597037211198]
  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.
  arXiv  Detail & Related papers  (2026-05-30T04:29:52Z)
• Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking [81.34609950921023]
  Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining.<n>We propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues.
  arXiv  Detail & Related papers  (2026-05-21T14:25:28Z)
• SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction [7.708279811172532]
  Imitation learning for robotic grasping is often plagued by the multimodal problem.<n>Standard imitation learning policies fail by averaging these distinct actions into a single, invalid action.<n>We introduce SAM2Grasp, a novel framework that reformulating the task as a uni-modal, prompt-conditioned prediction problem.
  arXiv  Detail & Related papers  (2025-12-02T10:15:00Z)
• Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts [16.21786310193235]
  We propose a novel dynamic priors-based fine-tuning paradigm with fewer trainable parameters, dubbed Controllable-LPMoE.<n>We construct a lightweight dynamic mixed local priors extractor that captures diverse local priors from input images through heterogeneous convolutions.<n>We also design a bi-directional interaction adapter that employs cosine-aligned deformable attention and channel-oriented adaptive scale enhancement.
  arXiv  Detail & Related papers  (2025-10-24T03:03:59Z)
• Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos [58.156141601478794]
  Multi-object tracking (UAVT) aims to track multiple objects while maintaining consistent identities across frames of a given video.<n>Existing methods typically model motion cues and appearance separately, overlooking their interplay and resulting in suboptimal tracking performance.<n>We propose AMOT, which exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module.
  arXiv  Detail & Related papers  (2025-08-03T12:06:47Z)
• ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions [91.55655961014027]
  3D semantic occupancy and flow prediction are fundamental to understanding scene scene.<n>This paper proposes a vision-based framework with three targeted improvements.<n>Our purely convolutional architecture establishes new SOTA performance on multiple benchmarks for both semantic occupancy and joint semantic-flow prediction.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking.<n>DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget.<n>Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks [55.36987468073152]
  This paper proposes a novel Dual-Guided Spatial-Channel-Temporal (DG-SCT) attention mechanism. The DG-SCT module incorporates trainable cross-modal interaction layers into pre-trained audio-visual encoders. Our proposed model achieves state-of-the-art results across multiple downstream tasks, including AVE, AVVP, AVS, and AVQA.
  arXiv  Detail & Related papers  (2023-11-09T05:24:20Z)
• 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)
• Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes [19.810725397641406]
  We propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly. Our contributions are two-fold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth feature representation. Second, we propose a warping-based Motion Network to estimate the motion field of dynamic objects without using semantic prior.
  arXiv  Detail & Related papers  (2023-01-14T09:43:23Z)

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.