2d-to-3d topic

[CVPR 2017] Generation and reconstruction of 3D shapes via modeling multi-view depth maps or silhouettes

Amir-Arsalan

Create 3d rooms in blender from floorplans.

grebtsew

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

astra-vision

We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular c...

FORTH-ModelBasedTracker

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"

Nicholasli1995

An extension for Pixelorama that generates 3D voxel art out of 2D pixel art.

Orama-Interactive

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

NVlabs

SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

ai4ce

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

Sense-GVT

Extruding a 32-bit color image into a 3D mesh.

stevinz