Michael Fischer
@michi_fischer
Followers
202
Following
174
Media
12
Statuses
53
Research Scientist at Adobe Research
London
Joined March 2012
Check out our latest @Adobe selection tech that my colleague @vdeschaintre just presented at MAX ! See you in @Photoshop soon :)
I was at #AdobeMAX this week to present #projectSurfaceSwap! Our surface selection and replacement techs! Check it out here: https://t.co/l76025JQrb What a blast the Sneaks were!
0
0
3
A bit late to the party - abstained from X for a while - but excited to announce that our paper on stochastic gradient estimation for inverse rendering got accepted to ICCV 2025 - see you in Hawaii 🌴 w/ Tobias Ritschel & Zican Wang from UCL preprint: https://t.co/Hp7EzcjSPu
1
1
13
I'm super excited to announce that I've joined @AdobeResearch as a research scientist in London! Looking forward to what we'll do together - fascinating times to be in research! :)
3
0
23
The amazing @rtwiersma has upladed the SIGGRAPH Thesis Fast Forward 2025, and I'm proud to be one of the 6 selected candidates. 🥰🥳 A short 3-minute summary of my thesis research starts at the 6:20 mark:
1
0
6
📢 Check out SAMa, our latest work on material selection in 3D! It works on arbitrary 3D assets and achieves efficient click-to-selection times of less than 2 seconds! 🎓 PDF: https://t.co/P2X0UZWoaB Project: https://t.co/AOznkDPtFW --> More info in🧵
mfischer-ucl.github.io
Michael Fischer, PhD Student in AI and Computer Graphics at University College London (UCL).
🎓 We introduce SAMa! A material selection and segmentation model on 3D models in any format (3DGS, NeRF, Mesh). Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute: https://t.co/cl3KvzBLcw
0
2
12
🎓 We introduce SAMa! A material selection and segmentation model on 3D models in any format (3DGS, NeRF, Mesh). Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute: https://t.co/cl3KvzBLcw
3
35
141
The project was led by Michael Fischer ( https://t.co/c73tsz1DWv) during his internship at Adobe with a great team (if I say so myself!) @iliyang, @thibaultgroueix, Vova Kim, Tobias Ritschel and I.
0
2
3
🚨 We will present TEXsliders tomorrow morning at 9 at @siggraph in Mile High 2A ! Presented by the amazing @juliagviu !
📚@juliagviu will present our TexSliders work at Siggraph this summer! We show slider-like editability of generated textures for arbitrary dimensions! 🌟Paper and results with interactive sliders: https://t.co/FVQUX7pHUI
0
6
23
Super excited to present our work ZeroGrads at SIGGRAPH 2024. Learn how ZeroGrads can differentiate ANY arbitrary graphics pipeline on Monday, in the 2pm "Differentiable Rendering" session, or check out the project page: https://t.co/9bonP0Exqo
1
27
119
Our work RRM: Relightable assets using Radiance guided Material extraction was presented earlier this month at CGI2024 🌎in Geneva! Webpage: https://t.co/0Ts0vwcMCb 🧵 1/n
1
6
16
Are you frustrated of intermittently bad depth maps ruining your online pipeline 😫? Wish you could get fast 🚀 reuse of your previously predicted depth frames? Do you want shiny fast SOTA feedforward depth and meshes ✨? Introducing DoubleTake! https://t.co/GvHfIitPLL
8
41
265
Come check out our poster on NeRF Analogies at the @CVPR poster session now, #436! Looking forward to meeting everyone :) Project page: https://t.co/REhakEbsp0
0
0
8
I've had a great experience presenting my PhD research at the doctoral consortium at @EurographicsC, chaired by @vdeschaintre and Mina Luković, in sunny Cyprus. Lots of valuable feedback from both academia and industry!
1
0
15
Very happy to announce that our paper "NeRF Analogies " has been accepted to @CVPR! This is joint work with @thunguyenphuoc, @BozicAljaz, @flycooler and others at Meta - see y'all in Seattle :) Project page: https://t.co/REhakEaUzs arXiv preprint: https://t.co/tL1vo9TmoZ
3
6
44
Our work "NeRF Analogies" is available on arXiv today: https://t.co/tL1vo9TmoZ We leverage semantic correspondences from DiNO features to combine a source appearance with a desired target-geometry in 3D. Project page: https://t.co/REhakEaUzs
0
2
11
NeRF Analogies Example-Based Visual Attribute Transfer for NeRFs paper page: https://t.co/ztoqk3j0qC A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene. We here ask the question whether we can transfer the appearance from a
0
15
62
✨Want to kick back and relax post deadline? 📢📢Checkout the Siggraph Thesis Fast Forward 2024, fresh out of the oven! https://t.co/DcWA3Eh9no
0
5
24
📢 Permissively licensed SVBRDF Dataset! https://t.co/ct11LQXpAG 📚SVBRDF Ground truth Material Data with permissive license has been challenging to get or gather in the last few years. We present MatSynth, with 4000+ carefully curated materials with permissive licences
2
36
104
How well automatic methods today can understand hand-drawn abstract scene sketches? Paper: https://t.co/C2jYVQ2LEa Code: https://t.co/DD7epmcJiX Work by my Ph.D. student @BrsAhmed, in collaboration with @judyefan
#cvssp #PAI
4
25
68