GeoFix: Geometry Fixing for 4D Consistent Generation
cs.CV, cs.AI, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/Vchitect/VBench1https:
Project page: https://yeobinhong.github.io/GeoFix/1
Sources
- VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
- MEt3R: Measuring Multi-View Consistency in Generated Images
- ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
- VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
- Theoretical guarantees on the best-of-n alignment policy
- 4DNeX: Feed-Forward 4D Generative Modeling Made Easy
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards
- VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
- CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback
- Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
- GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
- LoRA: Low-Rank Adaptation of Large Language Models
- Segment Any Motion in Videos
- VBench: Comprehensive Benchmark Suite for Video Generative Models
- VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models
- MUSIQ: Multi-scale Image Quality Transformer
- Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
- Epipolar Geometry Improves Video Generation Models
- Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing
- Aligning Text-to-Image Models using Human Feedback
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