-
ETH Zürich
- Stanford, CA
-
00:10
(UTC -08:00) - sayands.github.io
- @debsarkar_sayan
Stars
🟣 Computer Vision interview questions and answers to help you prepare for your next machine learning and data science interview in 2024.
[3DV 2025] LoopSplat: Loop Closure by Registering 3D Gaussian Splats
Repository for WACV23 paper "Automatically Annotating Indoor Images with CAD Models via RGB-D Scans"
SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks
Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"
[CV4AEC Workshop CVPR 2024] Dataset + Evaluation Metrics
PyViz3D is a web-based visualizer for 3D objects and point clouds.
projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data
A quick guide (especially) for trending instruction finetuning datasets
[CVPR 2024, highlight] Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
Main source code repository of the Tamarin prover for security protocol verification.
A generic and robust calibration toolbox for multi-camera systems
Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs
Lecture notes and cheatsheets for Master's in Computer Science at ETH Zurich
Repo for visualization of MCSS outputs and its evaluation
CVPR2020. HOnnotate: A method for 3D Annotation of Hand and Object Poses
My implementation of various GAN (generative adversarial networks) architectures like vanilla GAN (Goodfellow et al.), cGAN (Mirza et al.), DCGAN (Radford et al.), etc.
A toolbox to iNNvestigate neural networks' predictions!
We introduce the ScanNet-Layout dataset for benchmarking general 3D room layout estimation from single view.
Source code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach"…
Depth-aware CNN for RGB-D Segmentation, ECCV 2018