Trending Research
Flow-Guided Transformer for Video Inpainting
hitachinsk/fgt
•
•
Especially in spatial transformer, we design a dual perspective spatial MHSA, which integrates the global tokens to the window-based attention.
OCR-free Document Understanding Transformer
clovaai/donut
•
•
Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
Collaborative Neural Rendering using Anime Character Sheets
Drawing images of characters with desired poses is an essential but laborious task in anime production.
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory needed for inference by half while retaining full precision performance.
Ranked #2 on
Language Modelling
on C4
KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints
facebookresearch/KeypointNeRF
•
•
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.
Ranked #1 on
Generalizable Novel View Synthesis
on ZJU-MoCap
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
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.
Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
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.
Ranked #1 on
Real-Time Object Detection
on COCO
Deep Patch Visual Odometry
We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO).
StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3
Notably, StyleFaceV is capable of generating realistic $1024\times1024$ face videos even without high-resolution training videos.
