ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

• URL: http://arxiv.org/abs/2607.01677v1
• Date: Thu, 02 Jul 2026 04:05:17 GMT
• Title: ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
• Abstract summary: Video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios.<n>We introduce textbfICDepth, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning.
• Score: 48.25349086337865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce \textbf{ICDepth}, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)~\textbf{SAND-Attention}, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)~\textbf{SRFM}, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames ($6$--$13\times$ less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.

Related papers

• Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection [1.2072875728151518]
  weakly supervised video anomaly detection (WSVAD) has emerged as a critical research frontier.<n>Most existing approaches formulate WSVAD within a Multiple Instance Learning (MIL) framework that relies on rigid, hand-crafted temporal priors to supervise anomaly scoring.<n>We propose an adaptive temporal modeling framework for WSVAD that explicitly accounts for variations in video dynamics across multiple temporal granularities.
  arXiv  Detail & Related papers  (2026-09-04T12:27:43Z)
• TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution [52.96050253456634]
  TRaM-VSR is a framework for adaptive token allocation using context-aware video priors and network-levels.<n>It is shown that TRaM-VSR accelerates inference significantly while preserving state-of-the-art reconstruction quality and robust temporal consistency.
  arXiv  Detail & Related papers  (2026-07-24T11:57:26Z)
• LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models [14.33633321388011]
  LongE2V is a novel approach that leverages pre-trained video diffusion priors to handle event-based video reconstruction.<n>By fine-tuning agressive video models, our approach mitigates high data efficiency and superior perceptual quality.<n>Experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks.
  arXiv  Detail & Related papers  (2026-07-09T17:59:52Z)
• DVD: Deterministic Video Depth Estimation with Generative Priors [87.46576463137801]
  DVD is the first framework to adapt pre-trained video diffusion models into single-pass depth regressors.<n>DVD achieves state-of-the-art zero-shot performance across benchmarks.<n>We fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.
  arXiv  Detail & Related papers  (2026-03-12T17:58:06Z)
• UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models [54.564740558030245]
  We present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism.<n>We also introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting.
  arXiv  Detail & Related papers  (2026-02-26T12:54:46Z)
• StableDPT: Temporal Stable Monocular Video Depth Estimation [14.453483279783908]
  We propose a novel approach that adapts any state-of-the-art image-based (depth) estimation model for video processing.<n>Our architecture builds upon an off-the-shelf Vision Transformer (ViT) encoder and enhances the Dense Prediction Transformer (DPT) head.<n> Evaluations on multiple benchmark datasets demonstrate improved temporal consistency, competitive state-of-the-art performance and on top 2x faster processing in real-world scenarios.
  arXiv  Detail & Related papers  (2026-01-06T08:02:14Z)
• Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models [64.92045568376705]
  Coherent Contextual Decoding (CCD) is a novel inference framework built upon two core innovations.<n>CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence.<n>Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step.
  arXiv  Detail & Related papers  (2025-11-26T09:49:48Z)
• Adapformer: Adaptive Channel Management for Multivariate Time Series Forecasting [49.40321003932633]
  Adapformer is an advanced Transformer-based framework that merges the benefits of CI and CD methodologies through effective channel management.<n>Adapformer achieves superior performance over existing models, enhancing both predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-11-18T16:24:05Z)
• Multi-modal Deepfake Detection and Localization with FPN-Transformer [21.022230340898556]
  We introduce a multi-modal deepfake detection and localization framework based on a Feature Pyramid-Transformer (FPN-Transformer)<n>A multi-scale feature pyramid is constructed through R-TLM blocks with localized attention mechanisms, enabling joint analysis of cross-context temporal dependencies.<n>We evaluate our approach on the test set of the IJCAI'25 DDL-AV benchmark, showing a good performance with a final score of 0.7535.
  arXiv  Detail & Related papers  (2025-11-11T09:33:39Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• UnLoc: Leveraging Depth Uncertainties for Floorplan Localization [80.55849461031879]
  UnLoc is an efficient data-driven solution for sequential camera localization within floorplans.<n>We introduce a novel probabilistic model that incorporates uncertainty estimation, modeling depth predictions as explicit probability distributions.<n>We evaluate UnLoc on large-scale synthetic and real-world datasets, demonstrating significant improvements in terms of accuracy and robustness.
  arXiv  Detail & Related papers  (2025-09-14T14:45:43Z)
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction [39.22287224290769]
  H3R is a hybrid framework that integrates latent fusion with attention-based feature aggregation.<n>By integrating both paradigms, our approach enhances generalization while converging 2$times$ faster than existing methods.<n>Our method supports variable-number and high-resolution input views while demonstrating robust cross-dataset generalization.
  arXiv  Detail & Related papers  (2025-08-05T05:56:30Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)

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.