AI Paper Atlas

Research map / Video / Video generation

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

Yu Li, Menghan Xia, Gongye Liu, Jianhong Bai, Xintao Wang, Conglang Zhang, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Yujiu Yang

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 random camera-pose guidance during Stage I video generation training (ablation)AdaViewPlanner Stage I · General-domain 4D human motion controlWA-MPJPE (mm): 127.68 -> 103.92Improved
add random camera-pose guidance during Stage I video generation training (ablation)AdaViewPlanner Stage I · TikTok (dance domain)WA-MPJPE (mm): 72.60 -> 71.65Improved
add random camera-pose guidance during Stage I video generation training (ablation)AdaViewPlanner Stage I · General domainPA-MPJPE (mm): 33.80 -> 35.70Hurt
add 3D RoPE for human motion tokens (ablation)AdaViewPlanner Stage I · General-domain 4D human motion controlWA-MPJPE (mm): 122.13 -> 103.92Improved
add 3D RoPE for human motion tokens (ablation)AdaViewPlanner Stage I · TikTok (dance domain)WA-MPJPE (mm): 82.59 -> 71.65Improved
train Stage I to full convergence instead of an early checkpoint (ablation)AdaViewPlanner · camera extraction reprojectionreprojection MSE: 0.181 -> 0.158Improved
add human motion conditioning to Stage II camera extraction (ablation)AdaViewPlanner Stage II · camera extraction reprojectionreprojection IoU: 0.226 -> 0.338Improved
predict absolute camera poses with motion branch instead of relative poses (ablation)AdaViewPlanner Stage II · camera extraction reprojectionreprojection MSE: 0.167 -> 0.158Improved
predict absolute camera poses with motion branch instead of relative poses (ablation)AdaViewPlanner Stage II · Human Missing RateHMR: 0.039 -> 0.018Improved
use video-model-based two-stage planning instead of re-implemented DanceCamera3DAdaViewPlanner · E.T. testsetText-Camera Consistency: 0.975 -> 1.125Improved
use video-model-based two-stage planning instead of E.T.AdaViewPlanner · E.T. testsetuser preference (%): 23.81 -> 61.90Improved
video-model-based planning vs E.T. on camera translation jerkAdaViewPlanner · E.T. testsetJerk_t: 0.001 -> 0.007Hurt

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