Zirui Wang Profile
Zirui Wang

@ziruiwang_

Followers
477
Following
1K
Media
18
Statuses
63

Postdoc and DPhil @AVLOxford

Joined August 2013
Don't wanna be here? Send us removal request.
@ziruiwang_
Zirui Wang
2 years
Thanks for sharing :) TLDR: Introducing an image evaluation method that assesses rendered images via images from other viewpoints, eliminating the need for ground truth. Primary use: assessing novel views in NVS tasks. โ›ณ๏ธ https://t.co/y0QdBq1ngl ๐Ÿ“„ https://t.co/yDBmW0fuqR
@zhenjun_zhao
Zhenjun Zhao
2 years
CrossScore: Towards Multi-View Image Evaluation and Scoring @ziruiwang_, @wenjing_bian, @omkarparkhi, @CarlYuhengRen, @viprad tl;dr: cross-attention+data from NVS optimisation->compare query image and multiple views of the same scene->IQA without GT https://t.co/3HNioqw61J
2
11
59
@ziruiwang_
Zirui Wang
13 days
Excited to share that our Oxford Day-and-Night dataset has been accepted to the NeurIPS 2025 Dataset track! See you in San Diego! ๐Ÿ“ฆ Dataset: https://t.co/FGOKTaKv5W ๐ŸŒ Project Page:
Tweet card summary image
huggingface.co
@zhenjun_zhao
Zhenjun Zhao
6 months
Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset @ziruiwang_, @wenjing_bian, @li_xinghui, @Yifu_Tao, Jianeng Wang, @MauriceFallon, Victor Adrian Prisacariu tl;dr: egocentric dataset with GT 3D and lighting variation for benchmarking
1
5
24
@zhenjun_zhao
Zhenjun Zhao
5 months
Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment @ziruiwang_, @ysbhalgat, @RayLi234, @viprad tl;dr: CrossScore helps active NVS https://t.co/HXSZHVYtWd
1
7
49
@zhenjun_zhao
Zhenjun Zhao
6 months
Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset @ziruiwang_, @wenjing_bian, @li_xinghui, @Yifu_Tao, Jianeng Wang, @MauriceFallon, Victor Adrian Prisacariu tl;dr: egocentric dataset with GT 3D and lighting variation for benchmarking
0
15
49
@ziruiwang_
Zirui Wang
10 months
Glad to see a couple of our methods featured (and getting beaten๐Ÿค•) in this video ๐Ÿ˜…
@twominutepapers
Two Minute Papers
10 months
NVIDIA Unveils AI For 150x Faster 3D Modeling! Full video: https://t.co/rEglRiYFSM
0
0
3
@ziruiwang_
Zirui Wang
10 months
Check out our diffusion based 3D object detection. Will be an oral presentation in 3DV 2025! https://t.co/Y0bnSkv7Dk #3dv #3dv2025
@wenjing_bian
Wenjing Bian
10 months
CatFree3D: Category-agnostic 3D Object Detection with Diffusion TL;DR: A diffusion-based 3DOD pipeline boosting accuracy & generalization, plus a new evaluation metric ๐Ÿ“„ https://t.co/GAkEhUGYPT w/ @ziruiwang_, Andrea Vedaldi Look forward to the oral presentation at #3DV2025
0
16
114
@ziruiwang_
Zirui Wang
10 months
0
0
3
@ziruiwang_
Zirui Wang
10 months
Just found a great paper Fast3R, processing 1000 images in Dust3R style in one go! https://t.co/91Is4oP4so Btw, training takes a week on 64 A100 ๐Ÿ˜… and inferencing 1500 images takes 5min on 1 A100
3
49
265
@ziruiwang_
Zirui Wang
10 months
I'm excited that our paper got into ICLR 2025! Great work done by @DavidLA05031686! This is another great work on camera localisation from our group @AVLOxford (other works are mostly from @ShuaiC8 and @wenjing_bian)
@ysbhalgat
Yash Bhalgat
10 months
๐Ÿ“ข Paper accepted to #ICLR2025 ๐ŸŽ‰ "GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting" TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching. ๐Ÿ”—: https://t.co/zK99FUQhCy
0
2
8
@sunjiao123sun_
Jiao Sun
1 year
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Canโ€™t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? ๐Ÿ˜ก
181
803
4K
@EleonoraSberg
Eleonora Svanberg
1 year
I'm a PhD student at @UniofOxford and I think I'm living in a fairytale :-) Foxes playing around in the snow at Magdalen College this morning โ€” absolutely magical!
975
11K
108K
@jingwu23
Jing Wu ๐Ÿ„
1 year
๐Ÿฅณ We are going to present our poster GaussCtrl at #ECCV2024 in Milan! @eccvconf Feel free to come and say hi to my poster if you're interested!! ๐Ÿ˜ผ ๐Ÿ—“๏ธ Thu 3 Oct 4:30 p.m. CEST โ€” 6:30 p.m. CEST, Poster #261 See you there!!๐Ÿ˜‰ ๐ŸŒ https://t.co/GKGVV4CFYa
0
1
4
@ziruiwang_
Zirui Wang
1 year
Come to our poster #297 this afternoon! #ECCV
@ziruiwang_
Zirui Wang
2 years
Thanks for sharing :) TLDR: Introducing an image evaluation method that assesses rendered images via images from other viewpoints, eliminating the need for ground truth. Primary use: assessing novel views in NVS tasks. โ›ณ๏ธ https://t.co/y0QdBq1ngl ๐Ÿ“„ https://t.co/yDBmW0fuqR
1
1
22
@ziruiwang_
Zirui Wang
1 year
๐Ÿค–Code release for our ๐—ด๐—ฟ๐—ผ๐˜‚๐—ป๐—ฑ-๐˜๐—ฟ๐˜‚๐˜๐—ต-๐—ณ๐—ฟ๐—ฒ๐—ฒ ๐—ถ๐—บ๐—ฎ๐—ด๐—ฒ ๐—พ๐˜‚๐—ฎ๐—น๐—ถ๐˜๐˜† ๐—ฎ๐˜€๐˜€๐—ฒ๐˜€๐˜€๐—บ๐—ฒ๐—ป๐˜ project: https://t.co/9L5pxbDhM0 See you at Milan!
@ziruiwang_
Zirui Wang
2 years
Thanks for sharing :) TLDR: Introducing an image evaluation method that assesses rendered images via images from other viewpoints, eliminating the need for ground truth. Primary use: assessing novel views in NVS tasks. โ›ณ๏ธ https://t.co/y0QdBq1ngl ๐Ÿ“„ https://t.co/yDBmW0fuqR
0
1
3
@ziruiwang_
Zirui Wang
1 year
ECCV Pro Tip: Double-check if your ๐๐‘ ๐œ๐จ๐๐ž on your poster and video is still valid! Some online QR code generators have expiration periods โ€” I learned this the hard way๐Ÿคฆโ€โ™‚๏ธ #ECCV
0
0
6
@ziruiwang_
Zirui Wang
1 year
Loving ๐ญ๐จ๐ซ๐œ๐ก.๐œ๐จ๐ฆ๐ฉ๐ข๐ฅ๐ž! Reduced my VRAM usage from 23GB โžก 14GB! It might need some setup and debugging though๐Ÿ› Highly recommend this doc ๐Ÿ“‘ https://t.co/Mfh88dTang
0
2
34
@ziruiwang_
Zirui Wang
1 year
๐ŸŽฅInterested in the latest ๐ฏ๐ข๐๐ž๐จ ๐๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง ๐ฆ๐จ๐๐ž๐ฅ๐ฌ? Take ๐Ÿ ๐ฆ๐ข๐ง to join our study on video quality โ€ exploring spatial, temporal, & multi-view consistency in generated videos. ๐Ÿ“Results & videos will be a part of a public dataset! โ›ณ๏ธ https://t.co/0UAA2TXmI2
1
6
42
@ziruiwang_
Zirui Wang
2 years
0
0
0
@ziruiwang_
Zirui Wang
2 years
Couldn't help but create a GPT too. It's only 6 days until the CVPR deadline, so why not create a bot that searches and formats BibTeX? Link https://t.co/DwGY1ZHklP
3
7
95