Skip to content
RobotWorld
← Back

InFlux++: benchmark and synthetic data for dynamic camera intrinsics

Loading video
Loading video

InFlux++ introduces a real-world dynamic intrinsics benchmark and large synthetic training dataset for estimating dynamic camera intrinsics from RGB in robotics and 3D vision.

InFlux相机内参camera intrinsics动态相机benchmark数据集dataset3D视觉3D vision机器人感知robot perceptionErichLiangTwitter
Category: perception
Author: @ErichLiang
Date: 2026-09-01T00:00:00
Duration: 37.467s
Source: https://x.com/ErichLiang/status/2094797112785432943
Reference: https://github.com/princeton-vl/InFlux

Related Videos

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO
4:25

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO

@rsasaki0109 · 102 views · 2026-08-29
目标检测open-vocabulary detectionSAM3
Insta360 X6: Spatial Capture turns 360 recordings into 3D Gaussian Splat scenes
0:30

Insta360 X6: Spatial Capture turns 360 recordings into 3D Gaussian Splat scenes

@justinryanio · 7 views · 2026-08-07
Insta360高斯泼溅Gaussian Splatting
VidMap: Exploiting temporal structure for video-based Structure-from-Motion
0:53

VidMap: Exploiting temporal structure for video-based Structure-from-Motion

@zador_pataki · 13 views · 2026-08-07
SLAMSfM三维重建
RoboSense Ships 719K LiDAR Units in H1 2026
0:08

RoboSense Ships 719K LiDAR Units in H1 2026

@techniahqrobot · 13 views · 2026-08-01
激光雷达LiDARRoboSense
Real-Time 3D Human Pose Estimation

Real-Time 3D Human Pose Estimation

@rsasaki0109 · 7 views · 2026-07-28
姿态估计3D视觉深度学习
ClothTransformer — high-quality cloth simulation dataset (493K frames)
0:13

ClothTransformer — high-quality cloth simulation dataset (493K frames)

@XingangP · 9 views · 2026-07-17
Twitter布料仿真