Computer Vision › Generation ›

Video Generation

1433 directly classified papers

Papers per year

Papers

TITAN-Guide: Taming Inference-Time Alignment for Guided Text-to-Video Diffusion Models ICCV 2025

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion ICCV 2025

DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion ICCV 2025

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025

SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations ICCV 2025

UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving ICCV 2025

GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling ICCV 2025

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models ICCV 2025

Diffusion-Based Extreme High-speed Scenes Reconstruction with the Complementary Vision Sensor ICCV 2025

RnGCam: High-speed video from rolling & global shutter measurements ICCV 2025

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models ICCV 2025

MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps ICCV 2025

TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis ICCV 2025

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance ICCV 2025

TACO: Taming Diffusion for in-the-wild Video Amodal Completion ICCV 2025

BezierGS: Dynamic Urban Scene Reconstruction with Bezier Curve Gaussian Splatting ICCV 2025

LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling ICCV 2025

VSRM: A Robust Mamba-Based Framework for Video Super-Resolution ICCV 2025

DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions ICCV 2025

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment ICCV 2025

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors ICCV 2025

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data ICCV 2025

Voyaging into Perpetual Dynamic Scenes from a Single View ICCV 2025

Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation ICCV 2025

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model CVPR 2025