AI Paper Atlas

Research map / Point clouds / Point cloud classification

Generative Point Tracking and Forecasting

Xuanchen Lu, Ang Cao, Chao Feng, Andrew Owens

CVPR 2026 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds

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
use diffusion (flow matching) loss instead of L1 regression (ablation)point tracking model · Tracking ablationAJ: 43.3 -> 53.7Improved
use diffusion loss instead of L2 regression (ablation)point tracking model · Tracking ablationAJ: 30.2 -> 53.7Improved
add factorization of query points during training (ablation)point tracking model · Tracking ablationAJ: 36.6 -> 53.7Improved
add tuned logit-normal noise schedule (ablation)point tracking model · Tracking ablationAJ: 51.6 -> 53.7Improved
use stride 1 instead of larger sliding window stride (ablation)forecasting model · Kubric forecastingFVMD (Scene): 23361 -> 17786 (stride 8 vs 1)Improved
lower context noise level (0.15 to 0.02) (ablation)forecasting model · Kubric forecastingFVMD (Scene): 21552 -> 17786Improved
lower context noise 0.02 to 0.05 (ablation)forecasting model · Kubric forecastingBest of K: 95.6 -> 92.7Mixed
increase tracking context frames from 1 to 8 before forecasting (ablation)unified model · Kubric and Physics101 forecastingforecast error: Physics101 18.99 -> 11.42Improved
train jointly on tracking and forecasting (unified) instead of tracking only (ablation)unified model · TAP-Vid DAVISAJ: 61.7 -> 59.9Hurt
unified training with in-domain motion prior under synthetic occlusion (ablation)unified model · Physics101 tracking with occlusiondelta_occ_avg: 68.8 -> 82.2Improved
unified training with out-of-domain motion prior (Kubric-trained, DAVIS eval) (ablation)unified model · DAVIS tracking with occlusiondelta_vis_avg: 75.6 -> 73.8Hurt
point-space flow matching model vs latent diffusion forecasterOurs (Forecasting Only) · Kubric MOVi-A forecastingBest of K: 127.0 -> 95.6Improved

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