https://github.com/CandleLabAI/MotionAura-ICLR-2025
공식 코드MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The goal of Video Inpainting is to fill in missing regions of a given video sequence with contents that are both spatially and temporally coherent. Video Inpainting, also known as video completion, has many real-world applications such as undesired object removal and video restoration.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
Fast and Accurate Tensor Completion with Total Variation Regularized Tensor Trains
Towards An End-to-End Framework for Flow-Guided Video Inpainting
Progressive Temporal Feature Alignment Network for Video Inpainting
The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting
Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Internal Video Inpainting by Implicit Long-range Propagation
Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
Improving Video Generation for Multi-functional Applications
INR-V: A Continuous Representation Space for Video-based Generative Tasks
Expression-aware video inpainting for HMD removal in XR applications
Towards Language-Driven Video Inpainting via Multimodal Large Language Models
Deep Video Inpainting Guided by Audio-Visual Self-Supervision
Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
VQ-NeRV: A Vector Quantized Neural Representation for Videos
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer
Trusted Video Inpainting Localization via Deep Attentive Noise Learning
Infusion: internal diffusion for inpainting of dynamic textures and complex motion
Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications
SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video
Learning Joint Spatial-Temporal Transformations for Video Inpainting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.