Skip to content
RobotWorld
← Back to Videos

ABot-Recon Streaming 3D Reconstruction

Loading video
Loading video

Amap’s open model uses 12-frame local context to recover camera trajectories and global point clouds at 24.45 FPS on KITTI-02.

SLAMAMapABot-Recon3D reconstructionStreamingStreaming ReconstructionSpatial Intelligence
Category: perception
Author: @IndieDevHailey
Date: 2026-08-29T00:00:00
Duration: 14.975s
Source: https://x.com/IndieDevHailey/status/2093526972781695310
Reference: https://github.com/amap-cvlab/ABot-Recon

Related Videos

ABot-Recon turns driving video into 3D scenes
0:16

ABot-Recon turns driving video into 3D scenes

@HuggingApps · 686 views · 2026-08-31
ABot-Recon3D reconstructionSpatial AI
DeepMind D4RT turns a video into a 4D world
3:33

DeepMind D4RT turns a video into a 4D world

@Alacritic_Super · 808 views · 2026-08-31
D4RT4D WorldWorld Models
VidMap: Exploiting temporal structure for video-based Structure-from-Motion
0:53

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

@zador_pataki · 565 views · 2026-08-07
SLAMSfMECCV2026
SLAM3R: Real-time 3D Scene from Single Video
1:10

SLAM3R: Real-time 3D Scene from Single Video

@LearnWithSubhan · 577 views · 2026-07-25
SLAMOpen SourcePerception
SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video
0:51

SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video

@0x0SojalSec · 504 views · 2026-10-09
Spatial Intelligence3D Scene UnderstandingVision-language models
Grounded API: Robot Perception and SLAM
1:14

Grounded API: Robot Perception and SLAM

@GroundedSI · 766 views · 2026-09-16
Robot perceptionSLAMHand Tracking

As an Amazon Associate, we earn from qualifying purchases.