5 citations · 5 across the 4 of their papers we have counts for
4 papers · 1 filter
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Zhijian Shu, Cheng Lin, Tao Xie +8
3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…
PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth
Bu Jin, Weize Li, Baihan Yang +9
Recent advancements in autonomous driving (AD) systems have highlighted the potential of world models in achieving robust and generalizable performance across both ordinary and cha…
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
Bu Jin, Yupeng Zheng, Pengfei Li +12
3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, par…
PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Qiang Zhou, Weize Li, Lihan Jiang +4
Object anomaly detection is an important problem in the field of machine vision and has seen remarkable progress recently. However, two significant challenges hinder its research a…