AI Paper Atlas

Research map / Video / Video generation

Taming Camera-Controlled Video Generation with Verifiable Geometry Reward

Zhaoqing Wang, Xiaobo Xia, Zhuolin Bie, Jinlin Liu, Dongdong Yu, Jiawang Bian, Changhu Wang

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add online RL post-training with geometry reward (T2V)CamVerse SFT · RealEstate10K test (T2V)translation error: 0.0395 -> 0.0293Improved
add online RL post-training with geometry reward (T2V)CamVerse SFT · RealEstate10K test (T2V)rotation error: 0.6506 -> 0.5140Improved
add online RL post-training with geometry reward (I2V)CamVerse SFT · RealEstate10K test (I2V)rotation error: 0.5613 -> 0.4685Improved
add online RL post-training with geometry reward (I2V)CamVerse SFT · RealEstate10K test (I2V)visual quality: 5.02 -> 4.87Hurt
add dynamic videos to SFT data (ablation)CamVerse SFT · RealEstate10K 100-clip subset, image-to-videorotation error: 0.7306 -> 0.6506Improved
add shifted timestep scheduler (ablation)CamVerse SFT · RealEstate10K 100-clip subset, image-to-videorotation error: 0.6055 -> 0.5613Improved
add pose normalization (ablation)CamVerse SFT · RealEstate10K 100-clip subset, image-to-videorotation error: 0.7135 -> 0.5613Improved
use relative error for both translation and rotation (ablation)CamVerse GRPO · RealEstate10K 100-clip subset, image-to-videorotation error: 0.4537 -> 0.3286Improved
use dense segment-level reward instead of clip-level (ablation)CamVerse GRPO · RealEstate10K 100-clip subset, image-to-videorotation error: 0.3739 -> 0.3286Improved
use 3 SDE steps instead of 1 (ablation)CamVerse GRPO · RealEstate10K 100-clip subset, image-to-videorotation error: 0.4829 -> 0.3286Improved
use 3 SDE steps instead of 5 (ablation)CamVerse GRPO · RealEstate10K 100-clip subset, image-to-videotranslation error: 0.0278 -> 0.0238Improved
use balanced 4-4 samples instead of 1-1 (ablation)CamVerse GRPO · RealEstate10K 100-clip subset, image-to-videorotation error: 0.4330 -> 0.3286Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy