We have released COLMAP implementations of recent papers that make Structure-from-Motion robust to symmetries Surprise: none of these SOTA algorithms works consistently across datasets with the same hyperparams. More work needed for this difficult problem! github.com/cvg/sfm-disamb…

Warning: personal and emotional thread. Today is #MEAwarenessDay and we are heartbroken 💔. Our smart, athletic, ball-of-energy 10 year old is now bedridden and unable to stand or walk since January due to #LongCOVID and #MECFS. #LongCovidKids 👇🧵 1/

Implicit surfaces are great to reconstruct 3D humans. However, editing is hard because the geometry is represented by a single continuous function. In our upcoming #CVPR2023 paper, we overcome this by combining the advantages of explicit and implicit representations. 🧵👇

#CVPR Our AIT members are in Vancouver! Come to join our poster sessions! Here we show the schedule of our latest research grouped by poster sessions. Monday AM: Generalized Skill Embeddings

Happy to share our new paper on hair reconstruction that will appear at #ICCV2023, congrats to Vanessa Sklyarova and colleagues! We produce a detailed and personalized strand-based hairstyle from the monocular video. Project page: samsunglabs.github.io/NeuralHaircut More details in the thread 🧵

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page: ait.ethz.ch/emdb

Introducing "Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis". TL;DR: Novel views of faces at ultra-high 4K resolution from very few input images. Google AR & VR ETH Zurich AIT Lab #ICCV2023. syntec-research.github.io/Preface/ See thread below.

**Introducing AG3D**: Learning to Generate 3D Avatars from 2D Image Collections. 🔗Full Info: zj-dong.github.io/AG3D/ Catch our presentation at #ICCV2025 in Paris! 🗓️Date: Thursday 🕰️Time: 14:30 - 16:30 📌Paper ID: 1836 📍Location: Room "Foyer Sud" 088 🔽Details Below:

Given a monocular video as input, #HOLD reconstructs 3D hand and object surfaces for every frame without assuming a known object template. Our key insight is that interacting hands and objects provide complementary cues about each other's shape and pose. 1/4

In 2022, I finished 2 half marathons, 2 MTB races, and my computer vision research group was firing on all cylinders. In 2023 our lives were turned upside down by severe #LongCovid and #MECFS. 1/

Introducing "cads: unleashing the diversity of diffusion models through condition-annealed sampling" TL;DR: CADS is an inference method to increase the diversity of diffusion models while maintaining high quality. ETH Zurich AIT Lab #ICLR2024 ait.ethz.ch/cads see the 🧵

#CVPR2024 Highlight: HOLD (github.com/zc-alexfan/hold) is a self-supervised method to reconstruct 3D hand-object from RGB videos. It is category-agnostic, does not require an object template, generalizes to in-the-wild settings!

🚀 #CVPR2024 is almost here! Next week, AIT will present 8 papers at the conference. We're excited to share overviews of each project right here. Looking forward to connecting with you all in Seattle! 🌟 👇

Are you interested in hair reconstruction, human pose and shape estimation, digital human with clothing deformation, and hand-object interaction? Checkout our ECCV papers in the poster session at #ECCV2024! See 🧵.

Reconstructing 3D human-object interactions from images/videos is a key step towards realistic #3D humans for #AR/#VR and assistive #robots/#AI. To tackle this challenging problem my team and I have received an ERC Starting Grant 🎉 #ERCStG 📢 We look for 3x #PhD candidates!

A purely synthetic face prior can generalize to casual in-the-wild captures and stylized faces 🤯 I'm happy to share our SIGGRAPH Asia ➡️ Hong Kong paper “Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures.” syntec-research.github.io/Cafca/

A model that generates hand-object interactions based on text prompts! I'm happy to share our @SIGGRAPHAsiapaper “DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions”. diffh2o.github.io

Excited to present our recent work "LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models" next week at #NeurIPS2024. Please join us at our poster session next Thursday (December 12th) from 11:00 - 14:00 at East Exhibit Hall A-C #2604. 👇🧵

📢 I am #hiring 2x #PhD candidates to work on Human-centric #3D #ComputerVision at the University of #Amsterdam! 📢 The positions are funded by an #ERC #StartingGrant. For details and for submitting your application please see: werkenbij.uva.nl/en/vacancies/p… 🆘 Deadline: Feb 16 🆘

Sadly, I am no longer a professor at ETH (@eth_en) due to very severe #longCovid and #MECFS. ethrat.ch/de/ernennungen….