Weng Fei Low

Ph.D. student @ Institute of Data Science, National University of Singapore

[Weng Fei Low @wengflow]

Head over to our poster or visit our website to learn more about Deblur e-NeRF, as well as the event camera simulator & dataset released alongside.

🧵[4/4]

[Weng Fei Low @wengflow]

Thrilled to share my #ECCV2024 work with Gim Hee Lee (@gimhee_lee) on "Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions" tomorrow morning at Poster Session 1 (Poster #248)!

Project page: https://t.co/TFq2KwvqrG

🧵[1/4]

[Weng Fei Low @wengflow]

In this work, we propose a physically-accurate pixel bandwidth model that accounts for event motion blur, which we incorporate for blur-minimal NeRF reconstruction from motion-blurred events, generated under high-speed or low-light conditions.

🧵[3/4]

[Weng Fei Low @wengflow]

@eccvconf Any specific time?

[Weng Fei Low @wengflow]

@eccvconf The registration site states that "Each paper (MAIN or WORKSHOP) MUST be registered under a full, onsite registration type (no Student registration)". Does that mean student authors need to pay 695€ instead of 380€? This doesn't seem right 🤨

[Weng Fei Low @wengflow]

@eccvconf Are other reviewers & meta reviewers able to see my final rating & justification during the discussion period?

[Weng Fei Low @wengflow]

@AjdDavison Big data or not, I think manual labels are still required, as similarity is measured differently under different contexts or granularity, which the labels inform

[Weng Fei Low @wengflow]

I'll be presenting Robust e-NeRF, our work on robust NeRF reconstruction with moving event cameras, at #ICCV2023 this Friday morning (Poster 071, Foyer Sud).

Drop by to learn more and have a chat!
Check out our thread below too!

[Weng Fei Low @wengflow]

Super excited to share my #ICCV2023 work with Gim Hee Lee (@gimhee_lee) on "Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion"!

Project page: https://t.co/YP35o4ASjn
Paper: https://t.co/PLtqliQH1q
Code: https://t.co/bGCsYWSCBV

🧵[1/N]

[Weng Fei Low @wengflow]

Check out the website to learn more about Robust e-NeRF, as well as the event camera simulator & dataset released alongside.

Do also drop by the "3D from Multi-View and Sensors 2" @ FRI-AM poster session (10.30am - 12.30pm, 6 Oct 2023) to have a chat!

🧵[7/N=7]

[Weng Fei Low @wengflow]

Super excited to share my #ICCV2023 work with Gim Hee Lee (@gimhee_lee) on "Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion"!

Project page: https://t.co/YP35o4ASjn
Paper: https://t.co/PLtqliQH1q
Code: https://t.co/bGCsYWSCBV

🧵[1/N]

[Weng Fei Low @wengflow]

2. A complementary pair of normalized reconstruction losses that can effectively generalize to arbitrary speed profiles and intrinsic parameter values without such prior knowledge

🧵[6/N]

[Weng Fei Low @wengflow]

@ICCVConference "Note, that you will also have an opportunity to upload a short 5-min video ... to present your work on the ICCV23 online platform" — Does this entail that the video is optional?

[Weng Fei Low @wengflow]

@ICCVConference I noticed the paper titles aren't updated to reflect the camera ready submission. Is that intended?

[Weng Fei Low @wengflow]

@ICCVConference do we need to register an author by the camera ready deadline?

[Weng Fei Low @wengflow]

Our code can be found at https://t.co/tz7aZj9RhN.
We will also be presenting this work at #ECCV2022 (3:30PM - 5:30PM, 27 Oct @ Poster #64, Hall B). Drop by to find out more!

🧵[4/N=4]

[Weng Fei Low @wengflow]

Thanks @neural_fields for featuring our work!
Minimal Neural Atlas is a novel explicit neural surface representation that can effectively learn a minimal atlas of 3 charts with distortion-minimal parameterization for surfaces of complex topology.

🧵[1/N]

[Neural Fields @neural_fields]

Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion (ECCV 2022)

Authors: Weng Fei Low, Gim Hee Lee

https://t.co/cHs8AE8RiF

#neuralfieldsoftheday

[Weng Fei Low @wengflow]

In contrast, prior works generally predefine the parametric domain, which unnecessarily constrains the boundary and topology of each chart

🧵[3/N]