Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

alpa-projects/alpa 28 Jan 2022

Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.

685
1.20 stars / hour

3D Vision with Transformers: A Survey

lahoud/3d-vision-transformers 8 Aug 2022

The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field.

Natural Language Processing Pose Estimation

116
0.97 stars / hour

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

facebookresearch/KeypointNeRF 10 May 2022

In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views.

3D Face Reconstruction 3D Human Reconstruction +2

84
0.96 stars / hour

Deep Patch Visual Odometry

princeton-vl/dpvo 8 Aug 2022

We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO).

Monocular Visual Odometry

84
0.84 stars / hour

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

bytedance/next-vit 12 Jul 2022

Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks.

140
0.82 stars / hour

Collaborative Neural Rendering using Anime Character Sheets

megvii-research/conr 12 Jul 2022

Drawing images of characters at desired poses is an essential but laborious task in anime production.

Neural Rendering

299
0.81 stars / hour

Reconstructing 3D Human Pose by Watching Humans in the Mirror

zju3dv/EasyMocap CVPR 2021

In this paper, we introduce the new task of reconstructing 3D human pose from a single image in which we can see the person and the person's image through a mirror.

3D Pose Estimation

1,642
0.74 stars / hour

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

wongkinyiu/yolov7 6 Jul 2022

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56. 8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100.

Real-Time Object Detection

4,378
0.58 stars / hour

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

google-research/jax3d 30 Jul 2022

Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize images of 3D scenes from novel views.

Novel View Synthesis

222
0.50 stars / hour