Zirui Wang
@ziruiwang_
Followers
477
Following
1K
Media
18
Statuses
63
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. โณ๏ธ https://t.co/y0QdBq1ngl ๐ https://t.co/yDBmW0fuqR
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
Excited to share that our Oxford Day-and-Night dataset has been accepted to the NeurIPS 2025 Dataset track! See you in San Diego! ๐ฆ Dataset: https://t.co/FGOKTaKv5W ๐ Project Page:
huggingface.co
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
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
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
Glad to see a couple of our methods featured (and getting beaten๐ค) in this video ๐
0
0
3
Check out our diffusion based 3D object detection. Will be an oral presentation in 3DV 2025! https://t.co/Y0bnSkv7Dk
#3dv #3dv2025
CatFree3D: Category-agnostic 3D Object Detection with Diffusion TL;DR: A diffusion-based 3DOD pipeline boosting accuracy & generalization, plus a new evaluation metric ๐ https://t.co/GAkEhUGYPT w/ @ziruiwang_, Andrea Vedaldi Look forward to the oral presentation at #3DV2025
0
16
114
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 ๐
and inferencing 1500 images takes 5min on 1 A100
3
49
265
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)
๐ข Paper accepted to #ICLR2025 ๐ "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. ๐: https://t.co/zK99FUQhCy
0
2
8
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Canโt believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? ๐ก
181
803
4K
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
๐ฅณ 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!! ๐ผ ๐๏ธ Thu 3 Oct 4:30 p.m. CEST โ 6:30 p.m. CEST, Poster #261 See you there!!๐ ๐ https://t.co/GKGVV4CFYa
0
1
4
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. โณ๏ธ https://t.co/y0QdBq1ngl ๐ https://t.co/yDBmW0fuqR
1
1
22
๐คCode release for our ๐ด๐ฟ๐ผ๐๐ป๐ฑ-๐๐ฟ๐๐๐ต-๐ณ๐ฟ๐ฒ๐ฒ ๐ถ๐บ๐ฎ๐ด๐ฒ ๐พ๐๐ฎ๐น๐ถ๐๐ ๐ฎ๐๐๐ฒ๐๐๐บ๐ฒ๐ป๐ project: https://t.co/9L5pxbDhM0 See you at Milan!
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. โณ๏ธ https://t.co/y0QdBq1ngl ๐ https://t.co/yDBmW0fuqR
0
1
3
ECCV Pro Tip: Double-check if your ๐๐ ๐๐จ๐๐ on your poster and video is still valid! Some online QR code generators have expiration periods โ I learned this the hard way๐คฆโโ๏ธ #ECCV
0
0
6
Loving ๐ญ๐จ๐ซ๐๐ก.๐๐จ๐ฆ๐ฉ๐ข๐ฅ๐! Reduced my VRAM usage from 23GB โก 14GB! It might need some setup and debugging though๐ Highly recommend this doc ๐ https://t.co/Mfh88dTang
0
2
34
๐ฅInterested in the latest ๐ฏ๐ข๐๐๐จ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง ๐ฆ๐จ๐๐๐ฅ๐ฌ? Take ๐ ๐ฆ๐ข๐ง to join our study on video quality โ exploring spatial, temporal, & multi-view consistency in generated videos. ๐Results & videos will be a part of a public dataset! โณ๏ธ https://t.co/0UAA2TXmI2
1
6
42
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