A partial open-source replication of D4RT: Efficiently Reconstructing Dynamic Scenes One D4RT at a Time (Google DeepMind, CVPR 2026), built using the pretrained VGGT-1B encoder and publicly available datasets.
computer-visiondeep-learningtransformerspytorchnerfvideo-understandingdepth-estimationcamera-pose-estimationdynamic-sceneskubricpoint-tracking4d-reconstructioncross-attentionvggtd4rttapvid
-
Updated
Aug 13, 2026 - Python