Preserve, Reveal, Expand: Towards Faithful 4D Video Editing with Region-Aware Conditioning and Benchmarking

arXiv:2605.20961 · cs.CV · Submitted 2026-05-20 · Read on arXiv

cs.CV

Submitted: 2026-05-20

Updated: 2026-09-26

Project page: https://ricepastem.github.io/PREX-Open

Terminology

• Consistency — 16× in this paper · explained in 3 episodes
• Diffusion Model — 14× in this paper · explained in 8 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Fidelity — 10× in this paper · explained in 2 episodes
• Diffusion Models — 8× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Failure Modes — 4× in this paper · explained in 3 episodes
• World Model — 3× in this paper · explained in 7 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Gaussian Splatting — 2× in this paper · explained in 4 episodes
• Optical Flow — 2× in this paper · explained in 2 episodes
• Point Clouds — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• DeepVerse: 4D Autoregressive Video Generation as a World Model
• Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
• TokenFlow: Consistent Diffusion Features for Consistent Video Editing
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation
• Generative Video Motion Editing with 3D Point Tracks
• FlashWorld: High-quality 3D Scene Generation within Seconds
• Vista4D: Video Reshooting with 4D Point Clouds
• Trace Anything: Representing Any Video in 4D via Trajectory Fields
• TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
• Yume: An Interactive World Generation Model
• Wan: Open and Advanced Large-Scale Video Generative Models
• ATI: Any Trajectory Instruction for Controllable Video Generation
• Boximator: Generating Rich and Controllable Motions for Video Synthesis
• NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
• FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
• VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models