Large motion poses a critical challenge in Video Frame Interpolation (VFI) task, as it requires accurate modeling of object correspondences across frames. Existing methods primarily rely on convolutional or attention-based models, which operate at the pixel or patch level. This inherently limits them to local object correspondences, making it difficult to capture frame-level object correspondences and often leading to failure under large motion. Inspired by the fundamental theorem of surface, we explore frame-level object correspondences through the lens of differential surface. The core idea is to represent video frames as 3D surfaces and align them by matching their surface properties, thereby achieving global surface alignment and frame-level object alignment.

Event cameras, with their capacity to provide high temporal resolution information between frames, are increasingly utilized for video frame interpolation (VFI) in challenging scenarios characterized by high-speed motion and significant occlusion. However, prevalent issues of blur and distortion within the keyframes and ground truth data used for training and inference in these demanding conditions are frequently overlooked. This oversight impedes the perceptual realism and multiscene generalization capabilities of existing event-based VFI (E-VFI) methods when generating interpolated frames. Motivated by the observation that semanticperceptual discrepancies between degraded and pristine images are considerably smaller than their image-level differences, we introduce EPA. This novel E-VFI framework diverges from approaches reliant on direct image-level supervision by constructing multilevel, degradation-insensitive semantic perceptual supervisory signals to enhance the perceptual realism and multi-scene generalization of the model's predictions. Specifically, EPA operates in two phases: it first employs a DINO-based perceptual extractor, a customized style adapter, and a reconstruction generator to derive multi-layered, degradation-insensitive semantic-perceptual features (S).

Existing interpolation methods use pre-trained video diffusion priors to generate intermediate frames between sparsely sampled keyframes. In the absence of 3D geometric guidance, these methods struggle to produce plausible results for complex, articulated human motions and offer limited control over the synthesized dynamics. In this paper, we introduce PoseFuse3DKeyframe Interpolator (PoseFuse3D-KI), a novel framework that integrates 3D human guidance signals into the diffusion process for Controllable Human-centric Keyframe Interpolation (CHKI). To provide rich spatial and structural cues for interpolation, our PoseFuse3D, a 3D-informed control model, features a novel SMPL-X encoder that transforms 3D geometry and shape into the 2D latent conditioning space, alongside a fusion network that integrates these 3D cues with 2D pose embeddings. For evaluation, we build CHKI-Video, a new dataset annotated with both 2D poses and 3DSMPL-X parameters. We show that PoseFuse3D-KI consistently outperforms state-of-the-art baselines on CHKI-Video, achieving a 9% improvement in PSNR and a 38% reduction in LPIPS. Comprehensive ablations demonstrate that our PoseFuse3D model improves interpolation fidelity.

In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames.

Motion modeling is critical in flow-based Video Frame Interpolation (VFI).

Video frame interpolation, which aims to synthesize non-exist intermediate frames in a video sequence, is an important research topic in computer vision. Existing video frame interpolation methods have achieved remarkable results under specific assumptions, such as instant or known exposure time. However, in complicated real-world situations, the temporal priors of videos, i.e. frames per second (FPS) and frame exposure time, may vary from different camera sensors. When test videos are taken under different exposure settings from training ones, the interpolated frames will suffer significant misalignment problems. In this work, we solve the video frame interpolation problem in a general situation, where input frames can be acquired under uncertain exposure (and interval) time. Unlike previous methods that can only be applied to a specific temporal prior, we derive a general curvilinear motion trajectory formula from four consecutive sharp frames or two consecutive blurry frames without temporal priors. Moreover, utilizing constraints within adjacent motion trajectories, we devise a novel optical flow refinement strategy for better interpolation results. Finally, experiments demonstrate that one well-trained model is enough for synthesizing high-quality slow-motion videos under complicated real-world situations.

Noname manuscript No. (will be inserted by the editor) Abstract Video Frame Interpolation (VFI) remains a cornerstone in video enhancement, enabling temporal upscaling for tasks like slow-motion rendering, frame rate conversion, and video restoration. While classical methods rely on optical flow and learning-based models assume access to dense ground-truth, both struggle with occlusions, domain shifts, and ambiguous motion. This article introduces MiVID, a lightweight, self-supervised, diffusion-based framework for video interpolation. Our model eliminates the need for explicit motion estimation by combining a 3D U-Net backbone with transformer-style temporal attention, trained under a hybrid masking regime that simulates occlusions and motion uncertainty. The use of cosine-based progressive masking and adaptive loss scheduling allows our network to learn robust spatiotemporal representations without any high-frame-rate supervision.Our frame-Priyansh Srivastava School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha, India E-mail: priyansh0305@gmail.com Romit Chatterjee School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha, India E-mail: chatterjeeromit86@gmail.com Abir Sen (Corresponding Author) School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha, India E-mail: abir.senfcs@kiit.ac.in MiVID is trained entirely on CPU using the datasets and 9-frame video segments, making it a low-resource yet highly effective pipeline.

In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames.

Motion modeling is critical in flow-based Video Frame Interpolation (VFI).