Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence

• URL: http://arxiv.org/abs/2512.04619v1
• Date: Thu, 04 Dec 2025 09:48:12 GMT
• Title: Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
• Authors: Tianyu Yuan, Yuanbo Yang, Lin-Zhuo Chen, Yao Yao, Zhuzhong Qian,
• Abstract summary: HeFT (Head-Frequency Tracker) is a zero-shot point tracking framework that leverages visual priors of pretrained video diffusion models.<n>We analyze the internal representations of Video Diffusion Transformer (VDiT) to better understand how they encode information.<n>HeFT state-of-the-art zero-shot tracking performance, approaching the accuracy of supervised methods.
• Score: 12.086472765573278
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we introduce HeFT (Head-Frequency Tracker), a zero-shot point tracking framework that leverages the visual priors of pretrained video diffusion models. To better understand how they encode spatiotemporal information, we analyze the internal representations of Video Diffusion Transformer (VDiT). Our analysis reveals that attention heads act as minimal functional units with distinct specializations for matching, semantic understanding, and positional encoding. Additionally, we find that the low-frequency components in VDiT features are crucial for establishing correspondences, whereas the high-frequency components tend to introduce noise. Building on these insights, we propose a head- and frequency-aware feature selection strategy that jointly selects the most informative attention head and low-frequency components to enhance tracking performance. Specifically, our method extracts discriminative features through single-step denoising, applies feature selection, and employs soft-argmax localization with forward-backward consistency checks for correspondence estimation. Extensive experiments on TAP-Vid benchmarks demonstrate that HeFT achieves state-of-the-art zero-shot tracking performance, approaching the accuracy of supervised methods while eliminating the need for annotated training data. Our work further underscores the promise of video diffusion models as powerful foundation models for a wide range of downstream tasks, paving the way toward unified visual foundation models.

Related papers

• From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection [60.11169426478452]
  This paper aims to introduce fixation information to assist the detection of salient objects under weak supervision.<n>We propose a Position and Semantic Embedding (PSE) module to provide location and semantic guidance during the feature learning process.<n>An Intra-Inter Mixed Contrastive (MCII) model improves thetemporal modeling capabilities under weak supervision.
  arXiv  Detail & Related papers  (2025-06-30T05:01:40Z)
• Emergent Temporal Correspondences from Video Diffusion Transformers [30.83001895223298]
  We introduce DiffTrack, the first quantitative analysis framework designed to answer this question.<n>Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching.<n>We extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training.
  arXiv  Detail & Related papers  (2025-06-20T17:59:55Z)
• AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection [57.649223695021114]
  We present a novel weakly supervised framework that leverages audio-visual collaboration for robust video anomaly detection.<n>Our framework demonstrates superior performance across multiple benchmarks, with audio integration significantly boosting anomaly detection accuracy.
  arXiv  Detail & Related papers  (2025-04-06T13:59:16Z)
• FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection [4.015022008487465]
  Large-scale pre-trained video encoders tend to introduce background clutter and irrelevant semantics, leading to context confusion and boundaries.<n>We propose a frequency-aware decoupling network that improves action discriminability by filtering out noisy semantics captured by pre-trained models.<n>Our method achieves state-of-the-art performance on temporal action detection benchmarks.
  arXiv  Detail & Related papers  (2025-04-01T10:57:37Z)
• ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos [41.45750971432533]
  Video diffusion models (VDMs) facilitate the generation of high-quality videos.<n>Recent studies have uncovered the existence of "golden noises" that can enhance video quality during generation.<n>We propose ScalingNoise, a plug-and-play inference-time search strategy that identifies golden initial noises for the diffusion sampling process.
  arXiv  Detail & Related papers  (2025-03-20T17:54:37Z)
• DINTR: Tracking via Diffusion-based Interpolation [12.130669304428565]
  This work proposes a novel diffusion-based methodology to formulate the tracking task. Our INterpolation TrackeR (DINTR) presents a promising new paradigm and achieves a superior multiplicity on seven benchmarks across five indicator representations.
  arXiv  Detail & Related papers  (2024-10-14T00:41:58Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.<n>We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion [30.6593929365917]
  Video saliency prediction aims to identify regions in a video that attract human attention and gaze, driven by bottom-up features from the video and top-down processes like memory and cognition.<n>Existing methods primarily focus on modeling perceptual information while neglecting the reasoning process facilitated by language.<n>In this paper, we propose CaRDiff, a framework that imitates the process by integrating a multimodal large language model (MLLM), a grounding module, and a diffusion model.
  arXiv  Detail & Related papers  (2024-08-21T21:40:30Z)
• TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
  We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects. generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
  arXiv  Detail & Related papers  (2023-12-01T15:24:38Z)
• No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection [52.03562682785128]
  Temporal video grounding aims to retrieve the time interval of a language query from an untrimmed video. A significant challenge in TVG is the low "Semantic Noise Ratio (SNR)", which results in worse performance with lower SNR. We propose a no-frills TVG model that consists of two core modules, namely multi-scale neighboring attention and zoom-in boundary detection.
  arXiv  Detail & Related papers  (2023-07-20T04:12:10Z)
• Video Salient Object Detection via Contrastive Features and Attention Modules [106.33219760012048]
  We propose a network with attention modules to learn contrastive features for video salient object detection. A co-attention formulation is utilized to combine the low-level and high-level features. We show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-03T17:40:32Z)
• iffDetector: Inference-aware Feature Filtering for Object Detection [70.8678270164057]
  We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors. IFF performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead.
  arXiv  Detail & Related papers  (2020-06-23T02:57:29Z)

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.