@Annika_Thomas_ Profile picture

Annika Thomas

@Annika_Thomas_

PhD Candidate @MIT | Prev: @Stanford aero/astro, @Columbia MechE | Interests: Robotic Perception, Intelligent Systems, Autonomy in Space

Joined November 2013
Similar User
Andreas Backhaus photo

@a_backhaus

Tom Bock photo

@galunga70

COReAstro photo

@CORAstro

Sismo photo

@SismoAstroberry

madison photo

@maddsnajima

Mike 🇨🇦 photo

@lethbridge

Sawab 🇵🇸 photo

@SawabAwwad

Kristopher photo

@KristopherBryce

Aaron photo

@aacanode19

Malik photo

@_leekie

Katieee photo

@carnsasada

Dler's Toughts photo

@Freedom_MENA

bad guy.🇧🇸🇱🇨 photo

@irvinbrownmusic

SAGE photo

@whatissage

Trinidy🖤 photo

@ef_sociopath

Annika Thomas Reposted

Annika Thomas, a PhD candidate studying Mechanical Engineering at MIT working in the Aerospace Controls Laboratory, teaches robots how to perceive the world and align frames with other robots.

Tweet Image 1

Annika Thomas Reposted

Targeting Monday, March 4 for a Falcon 9 launch of our 10th dedicated smallsat rideshare mission with 53 spacecraft on board from Space Launch Complex 4 East in California → spacex.com/launches

Tweet Image 1

Annika Thomas Reposted

The computer vision class at @MIT has nearly doubled in size since just last year!! Looking forward to teaching close to 700 students this term alongside the amazing @vincesitzmann, Mina Konakovic Lukovic, and Kaiming He 😁😁😁


Accepted to #ICRA2024!

🚨 New Paper Alert! 📄✨ Check out the very first fully decentralized multiagent trajectory planner that uses segmentation for frame alignment 🌐🤖 Featuring: 1️⃣ Uncertainty-aware planning 🤔 2️️⃣ Novel frame alignment pipeline 🖼️ 🔬🌎 Simulations & real-world tests!



Annika Thomas Reposted

Ok this is kinda neat: If you give researchrabbit.ai a scientific paper it will generate a network of references and citations!

Tweet Image 1

Annika Thomas Reposted

Get crisp 3D Gaussian splats from blurry inputs 🤯 Capturing sharp videos is often impossible because of lens defocusing, object motion or camera shake. And 3DGS learns to fit this. "Deblurring 3DGS" optimizes a small MLP to model the scene blurriness! More details below ⬇️⬇️


Annika Thomas Reposted

At some point, as a working woman, you start seeing other women disappear. It begins slowly. You are on a Zoom call and you are the only female face. You are in a meeting room and someone presumes you are not good at what you do because you are so 'well-dressed'.


Annika Thomas Reposted

Academics will spend a full work day reading half an article then take 3 books onboard a 2 hour flight


Annika Thomas Reposted

We all know Midjourney AI can make some very professional images. But what about random boring photos of everyday people? I found a way to do so, and it's scary just how realistic they are. 9 examples:


Annika Thomas Reposted

🧵 The historic NYT v. @OpenAI lawsuit filed this morning, as broken down by me, an IP and AI lawyer, general counsel, and longtime tech person and enthusiast. Tl;dr - It's the best case yet alleging that generative AI is copyright infringement. Thread. 👇

Tweet Image 1

Annika Thomas Reposted

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️


Annika Thomas Reposted

Happy to share Gaussian Splatting SLAM rmurai.co.uk/projects/Gauss… We show the first 3DGS-based Monocular RGB SLAM, the hardest SLAM setting. Using 3D Gaussians as a unified representation, the method only requires RGB images - No need for SfM, depth sensor, or learned prior.


Annika Thomas Reposted

New research shows a method of how to use 3D Gaussian Splatting without pre-computed camera poses. Using 'COLMAP-Free 3D Gaussian Splatting', we can improve previous approaches in view synthesis and camera pose estimation under large motion changes. x.com/xiaolonw/statu…

3D Gaussian Splatting is great, but can it work without the pre-computed camera poses? Introducing: COLMAP-Free 3D Gaussian Splatting Our recent work shows not only it can, but 3D Gaussians make camera pose estimation easy (compared to NeRF) along with reconstruction. 👇🧵



Annika Thomas Reposted

Seeing some qs on what Gemini *is* (beyond the zodiac :). Best way to understand Gemini’s underlying amazing capabilities is to see them in action, take a look ⬇️


Annika Thomas Reposted

Reinforcement learning explained twitter.com/i/status/17310…


Loading...

Something went wrong.


Something went wrong.