Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation

• URL: http://arxiv.org/abs/2604.01700v1
• Date: Thu, 02 Apr 2026 06:58:46 GMT
• Title: Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation
• Abstract summary: Video frame aims to synthesize realistic intermediate frames between given endpoints while adhering to specific motion semantics.<n>We propose a novel bidirectional framework that enforces symmetry between forward and backward generation trajectories.<n>Our method achieves state-of-the-art performance in imaging quality, motion smoothness, and dynamic control on both 37-frame and 73-frame tasks.
• Score: 25.677744104220853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video frame interpolation aims to synthesize realistic intermediate frames between given endpoints while adhering to specific motion semantics. While recent generative models have improved visual fidelity, they predominantly operate in a unidirectional manner, lacking mechanisms to self-verify temporal consistency. This often leads to motion drift, directional ambiguity, and boundary misalignment, especially in long-range sequences. Inspired by the principle of temporal cycle-consistency in self-supervised learning, we propose a novel bidirectional framework that enforces symmetry between forward and backward generation trajectories. Our approach introduces learnable directional tokens to explicitly condition a shared backbone on temporal orientation, enabling the model to jointly optimize forward synthesis and backward reconstruction within a single unified architecture. This cycle-consistent supervision acts as a powerful regularizer, ensuring that generated motion paths are logically reversible. Furthermore, we employ a curriculum learning strategy that progressively trains the model from short to long sequences, stabilizing dynamics across varying durations. Crucially, our cyclic constraints are applied only during training; inference requires a single forward pass, maintaining the high efficiency of the base model. Extensive experiments show that our method achieves state-of-the-art performance in imaging quality, motion smoothness, and dynamic control on both 37-frame and 73-frame tasks, outperforming strong baselines while incurring no additional computational overhead.

Related papers

• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models [15.39037309359101]
  Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile.<n>We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation.<n>For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal.
  arXiv  Detail & Related papers  (2026-08-21T12:28:36Z)
• From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation [39.022447753493346]
  Event-based cameras capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision.<n>We propose a hybrid-supervised framework for continuous-time optical flow estimation, grounded in the principle of Spatio-temporal Structural Consistency (STSC)<n>Our method achieves state-of-the-art performance in both continuous-time and standard optical flow estimation, demonstrating the effectiveness of the proposed learning paradigm.
  arXiv  Detail & Related papers  (2026-05-25T08:24:23Z)
• Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency [74.90075313101933]
  This paper revisits the same optical-flow primitive through a more local supervision design.<n>We use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop.<n>To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:53:31Z)
• From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation [54.68405211129937]
  Exo-Seqto-Ego video generation aims to synthesize a first-person view from a synchronized third-person and corresponding camera poses.<n> synchronized exo-ego data inherently introduces substantial-temporal discontinuities, violating the smooth-motion assumptions of standard video generation benchmarks.<n>We propose Syn2Ex-Forcing, a sequential sequence model that interpolates between the source and target videos to form a single continuous signal.
  arXiv  Detail & Related papers  (2026-04-15T12:32:25Z)
• FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving [11.275815014211046]
  Building a learning-based closed-loop simulator for autonomous driving poses three major challenges.<n>Long-horizon temporal and cross-view consistency, mitigating autoregressive degradation under iterative self-conditioning, and satisfying low-latency inference constraints.<n>We propose FAR-Drive, a frame-level autoregressive video generation framework for autonomous driving.
  arXiv  Detail & Related papers  (2026-03-16T07:40:13Z)
• Towards Arbitrary Motion Completing via Hierarchical Continuous Representation [64.6525112550758]
  We propose a novel parametric activation-induced hierarchical implicit representation framework, called NAME, based on Implicit Representations (INRs)<n>Our method introduces a hierarchical temporal encoding mechanism that extracts features from motion sequences at multiple temporal scales, enabling effective capture of intricate temporal patterns.
  arXiv  Detail & Related papers  (2025-12-24T14:07:04Z)
• WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance [17.295532380360992]
  WorldForge is a training-free, inference-time framework composed of three tightly coupled modules.<n>Our framework is plug-and-play and model-agnostic, enabling broad applicability across various 3D/4D tasks.
  arXiv  Detail & Related papers  (2025-09-18T16:40:47Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better [61.381599921020175]
  Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts.<n>Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion.<n>We propose the Tracktention Layer, a novel architectural component that explicitly integrates motion information using point tracks.
  arXiv  Detail & Related papers  (2025-03-25T17:58:48Z)
• Motion-Aware Generative Frame Interpolation [23.380470636851022]
  Flow-based frame methods ensure motion stability through estimated intermediate flow but often introduce severe artifacts in complex motion regions.<n>Recent generative approaches, boosted by large-scale pre-trained video generation models, show promise in handling intricate scenes.<n>We propose Motion-aware Generative frame (MoG) that synergizes intermediate flow guidance with generative capacities to enhance fidelity.
  arXiv  Detail & Related papers  (2025-01-07T11:03:43Z)
• Triplet Attention Transformer for Spatiotemporal Predictive Learning [9.059462850026216]
  We propose an innovative triplet attention transformer designed to capture both inter-frame dynamics and intra-frame static features. The model incorporates the Triplet Attention Module (TAM), which replaces traditional recurrent units by exploring self-attention mechanisms in temporal, spatial, and channel dimensions.
  arXiv  Detail & Related papers  (2023-10-28T12:49:33Z)
• Modeling Continuous Motion for 3D Point Cloud Object Tracking [54.48716096286417]
  This paper presents a novel approach that views each tracklet as a continuous stream. At each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank. To enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed.
  arXiv  Detail & Related papers  (2023-03-14T02:58:27Z)
• Modelling Latent Dynamics of StyleGAN using Neural ODEs [52.03496093312985]
  We learn the trajectory of independently inverted latent codes from GANs. The learned continuous trajectory allows us to perform infinite frame and consistent video manipulation. Our method achieves state-of-the-art performance but with much less computation.
  arXiv  Detail & Related papers  (2022-08-23T21:20:38Z)
• TimeLens: Event-based Video Frame Interpolation [54.28139783383213]
  We introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both synthesis-based and flow-based approaches. We show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods.
  arXiv  Detail & Related papers  (2021-06-14T10:33:47Z)

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.