BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions

• URL: http://arxiv.org/abs/2412.11365v2
• Date: Sun, 29 Dec 2024 08:11:31 GMT
• Title: BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
• Authors: Wonyong Seo, Jihyong Oh, Munchurl Kim,
• Abstract summary: Existing Video Frame (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions. We propose Bidirectional Motion field (BiM) to effectively describe non-uniform motions. BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively.
• Score: 28.455538651097562
• License:
• Abstract: Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.

Related papers

• Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields [39.214857326425204]
  Video Frame Interpolation (VFI) aims to generate intermediate video frames between consecutive input frames. We propose a novel event-based VFI framework with cross-modal asymmetric bidirectional motion field estimation. Our method shows significant performance improvement over the state-of-the-art VFI methods on various datasets.
  arXiv  Detail & Related papers  (2025-02-19T13:40:43Z)
• Generalizable Implicit Motion Modeling for Video Frame Interpolation [51.966062283735596]
  Motion is critical in flow-based Video Frame Interpolation (VFI) We introduce General Implicit Motion Modeling (IMM), a novel and effective approach to motion modeling VFI. Our GIMM can be easily integrated with existing flow-based VFI works by supplying accurately modeled motion.
  arXiv  Detail & Related papers  (2024-07-11T17:13:15Z)
• Motion-aware Latent Diffusion Models for Video Frame Interpolation [51.78737270917301]
  Motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. We propose a novel diffusion framework, motion-aware latent diffusion models (MADiff) Our method achieves state-of-the-art performance significantly outperforming existing approaches.
  arXiv  Detail & Related papers  (2024-04-21T05:09:56Z)
• Motion-Aware Video Frame Interpolation [49.49668436390514]
  We introduce a Motion-Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, but also effectively reduces the required computational cost and complexity.
  arXiv  Detail & Related papers  (2024-02-05T11:00:14Z)
• A Multi-In-Single-Out Network for Video Frame Interpolation without Optical Flow [14.877766449009119]
  deep learning-based video frame (VFI) methods have predominantly focused on estimating motion between two input frames. We propose a multi-in-single-out (MISO) based VFI method that does not rely on motion vector estimation. We introduce a novel motion perceptual loss that enables MISO-VFI to better capture the vectors-temporal within the video frames.
  arXiv  Detail & Related papers  (2023-11-20T08:29:55Z)
• Boost Video Frame Interpolation via Motion Adaptation [73.42573856943923]
  Video frame (VFI) is a challenging task that aims to generate intermediate frames between two consecutive frames in a video. Existing learning-based VFI methods have achieved great success, but they still suffer from limited generalization ability. We propose a novel optimization-based VFI method that can adapt to unseen motions at test time.
  arXiv  Detail & Related papers  (2023-06-24T10:44:02Z)
• Learning Comprehensive Motion Representation for Action Recognition [124.65403098534266]
  2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing inter-frame connections while still suffering the limited temporal receptive field or high latency. We propose a Channel-wise Motion Enhancement (CME) module to adaptively emphasize the channels related to dynamic information with a channel-wise gate vector. We also propose a Spatial-wise Motion Enhancement (SME) module to focus on the regions with the critical target in motion, according to the point-to-point similarity between adjacent feature maps.
  arXiv  Detail & Related papers  (2021-03-23T03:06:26Z)
• FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation [97.99012124785177]
  FLAVR is a flexible and efficient architecture that uses 3D space-time convolutions to enable end-to-end learning and inference for video framesupervised. We demonstrate that FLAVR can serve as a useful self- pretext task for action recognition, optical flow estimation, and motion magnification.
  arXiv  Detail & Related papers  (2020-12-15T18:59:30Z)

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.