LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation

arXiv:2609.38146 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://jsxzs.github.io/LIFT

Terminology

• Distillation — 29× in this paper · explained in 2 episodes
• Self-distillation — 11× in this paper · explained in 6 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Consistency — 10× in this paper · explained in 3 episodes
• Diffusion Model — 10× in this paper · explained in 8 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Diffusion Models — 7× in this paper · explained in 6 episodes
• On-Policy Distillation — 6× in this paper · explained in 3 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Ablation study — 4× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Sparsity — 4× in this paper · explained in 4 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Anchor Loss — 3× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 3× in this paper
• World Model — 3× in this paper · explained in 7 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Flow Matching — 2× in this paper · explained in 8 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 2× in this paper
• On-policy Self-Distillation (OPSD) — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Frechet Video Distance — 1× in this paper
• GRPO — 1× in this paper · explained in 6 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Learned Perceptual Image Patch Similarity — 1× in this paper
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Success Rate of Entity — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• SAM 3: Segment Anything with Concepts
• Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation
• Flow-OPD: On-Policy Distillation for Flow Matching Models
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation
• CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
• Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
• Depth Anything 3: Recovering the Visual Space from Any Views
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
• Yume-1.5: A Text-Controlled Interactive World Generation Model
• DINOv2: Learning Robust Visual Features without Supervision
• Seedance 2.0: Advancing Video Generation for World Complexity
• Advancing Open-source World Models
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• Wan: Open and Advanced Large-Scale Video Generative Models
• SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
• EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
• Qwen-Image-2.0-RL Technical Report

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