Highlights
- Pro
Stars
A JS library to find the convex hull of a finite set of 3d points
ODAM: Object Detection, Association, and Mapping using Posed RGB Video
Exploring Relational Context for Multi-Task Dense Prediction [ICCV 2021]
Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)
CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
Submanifold sparse convolutional networks
[CVPR 2020 Oral] A differentiable framework for 3D registration
Code release for NeRF (Neural Radiance Fields)
Code Release for CVPR 2020, "ACNe: Attentive Context Normalizationfor Robust Permutation-Equivariant Learning"
My personal note about local and global descriptor
Deforming kernels to adapt towards object deformation. In ICLR 2020.
[CVPR'19] Dataset and code used in the research project Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Codebase for Image Classification Research, written in PyTorch.
Semantic Understanding of Foggy Scenes with Purely Synthetic Data
Attentive Single-tasking of Multiple Tasks
A PyTorch implementation of EfficientNet
PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"
Package to evaluate interactive segmentation with scribbles at DAVIS dataset.
Detail-Preserving Pooling in Deep Networks (CVPR 2018)
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Latex code for making neural networks diagrams