Skip to content
RobotWorld

Videos

WaterfallPagination
Filtered by:TechnologyVision & 3D PerceptionClear all
GaussiAnimate: Compressing 4D Capture Into a Rigged 3D Asset with Secondary Dynamics
1:00

GaussiAnimate: Compressing 4D Capture Into a Rigged 3D Asset with Secondary Dynamics

@yuliangxiu · 301 views · 2026-10-11
GaussiAnimate4D Capture
DirtyMoCap: Robust Motion Capture from Noisy, Unconstrained Markers
0:23

DirtyMoCap: Robust Motion Capture from Noisy, Unconstrained Markers

@yuliangxiu · 261 views · 2026-10-11
Motion CaptureDirtyMoCap
SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video
0:51

SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video

@0x0SojalSec · 639 views · 2026-10-09
Spatial Intelligence3D Scene Understanding
image-blaster: One Photo Becomes an Explorable 3D World
2:07

image-blaster: One Photo Becomes an Explorable 3D World

@Antonio_RodriIA · 273 views · 2026-10-09
3D GenerationGaussian Splatting
COSMI: Compositional Human-Object Interaction Dataset and Diffusion Model
0:37

COSMI: Compositional Human-Object Interaction Dataset and Diffusion Model

@GerardPonsMoll1 · 360 views · 2026-10-07
Human-Object InteractionDiffusion Transformer
Real-Time Neural Rendering for World Models
0:04

Real-Time Neural Rendering for World Models

@christiansafka · 354 views · 2026-10-06
Neural rendering3D Gaussian Splatting
OneCanvas: reproject video frames onto a single panoramic canvas so a stock 2D VLM reasons in 3D — SOTA on SQA3D, VSI-Bench and SPBench at an order of magnitude less compute

OneCanvas: reproject video frames onto a single panoramic canvas so a stock 2D VLM reasons in 3D — SOTA on SQA3D, VSI-Bench and SPBench at an order of magnitude less compute

@unknown · 535 views · 2026-06-19
VLMSpatial reasoning
NavVerse (CoRL 2026): a 200-scene, 10K-episode indoor-to-outdoor navigation benchmark — best zero-shot VLA reaches 11.6%, then halves across the door
2:51

NavVerse (CoRL 2026): a 200-scene, 10K-episode indoor-to-outdoor navigation benchmark — best zero-shot VLA reaches 11.6%, then halves across the door

@GhaffariMaani · 549 views · 2026-10-02
Embodied NavigationNavVerse
R3: streaming feed-forward 3D reconstruction via relative-pose regression — 372M params, 20+ FPS, thousands of frames, open-sourced for NeurIPS 2026
0:25

R3: streaming feed-forward 3D reconstruction via relative-pose regression — 372M params, 20+ FPS, thousands of frames, open-sourced for NeurIPS 2026

@CongrongX · 708 views · 2026-10-01
R33D reconstruction
NVIDIA open-sources Lyra 2.0: one image becomes an explorable 3D world, exportable to Isaac Sim for robot simulation
0:14

NVIDIA open-sources Lyra 2.0: one image becomes an explorable 3D world, exportable to Isaac Sim for robot simulation

@EngMoElgaraihy · 640 views · 2026-10-01
NVIDIALyra-2.0
AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed
1:06

AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed

@rsasaki0109 · 594 views · 2026-09-30
SLAMPerception
Matic: Build Home Robots Eyes First, Hands Later
1:22

Matic: Build Home Robots Eyes First, Hands Later

@mehul · 698 views · 2026-09-29
Home RobotService robots

As an Amazon Associate, we earn from qualifying purchases.