Tagged articles

3D Perception

3 articles · Page 1 of 1

Jun 8, 2026 · Artificial Intelligence

Meta’s VLM³ Boosts Depth Accuracy to 0.9 Using Qwen3‑VL‑4B for Unified 3D Tasks

Meta and Princeton introduce VLM³, a unified vision‑language framework built on Qwen3‑VL‑4B that models depth estimation, object‑level 3D understanding, pixel matching and camera pose estimation without extra encoders, achieving up to 0.90 depth accuracy and outperforming larger specialist models on multiple benchmarks.

3D PerceptionDepth EstimationQwen3-VL-4B

0 likes · 15 min read

Meta’s VLM³ Boosts Depth Accuracy to 0.9 Using Qwen3‑VL‑4B for Unified 3D Tasks

AI Frontier Lectures

Jan 30, 2026 · Artificial Intelligence

How SplatSSC Revolutionizes Semantic Scene Completion with Depth‑Guided Gaussian Splatting

SplatSSC introduces a depth‑guided Gaussian splatting framework that replaces random primitive initialization with geometry‑aware priors and a decoupled aggregation module, achieving state‑of‑the‑art performance on indoor semantic scene completion while dramatically reducing computational overhead and eliminating floaters.

3D PerceptionAI researchGaussian Splatting

0 likes · 10 min read

How SplatSSC Revolutionizes Semantic Scene Completion with Depth‑Guided Gaussian Splatting

Amap Tech

Nov 15, 2023 · Artificial Intelligence

Vision‑Based Bird’s‑Eye‑View (BEV) Representation and Solutions for Autonomous Driving

Vision‑based Bird’s‑Eye‑View (BEV) transforms camera data into a scale‑invariant, geometry‑friendly top‑down map using perspective‑transformation modules such as Lift‑Splat‑Shoot and Pseudo‑LiDAR, incorporates deformable convolutions and attention, and underpins modern autonomous‑driving detectors like BEVDet, BEVDepth, Detr3D, BEVFormer and PETR, while future research targets depth‑estimation bottlenecks, multimodal transformer fusion, and foundation‑model generalization.

3D PerceptionBEV

0 likes · 19 min read

Vision‑Based Bird’s‑Eye‑View (BEV) Representation and Solutions for Autonomous Driving