Violeta
@violetilla.bsky.social
Loud Spaniard. Maths & Software fan 👩🏻💻🐱💻 Dr in Computer Vision. Working on AI in media production 🎬 Mostly rants about AI, ML, FOSS, science, ethics, politics & public transport in the UK 🚴♀️🥾🌈 She/her
Pinned
Violeta
@violetilla.bsky.social
· Nov 14
Hello world, looking at being more active here. Let me know who I should be following here in the creative industries, AI, computer vision, 3D graphics, news, politics, software ethics, and cat pictures 🌼
Reposted by Violeta
FOSDEM 2026 - FOSDEM 2026 Main Track Deadline Reminder
Brussels / 31 January & 1 February 2026
fosdem.org
November 14, 2025 at 10:22 AM
Reposted by Violeta
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Botao Ye, Boqi Chen, @haofeixu.bsky.social, @danielbarath.bsky.social, @marcpollefeys.bsky.social
arxiv.org/abs/2511.07321
Botao Ye, Boqi Chen, @haofeixu.bsky.social, @danielbarath.bsky.social, @marcpollefeys.bsky.social
arxiv.org/abs/2511.07321
November 11, 2025 at 3:39 PM
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Botao Ye, Boqi Chen, @haofeixu.bsky.social, @danielbarath.bsky.social, @marcpollefeys.bsky.social
arxiv.org/abs/2511.07321
Botao Ye, Boqi Chen, @haofeixu.bsky.social, @danielbarath.bsky.social, @marcpollefeys.bsky.social
arxiv.org/abs/2511.07321
Reposted by Violeta
📢 Calling all devs & users of #opensource tools for research & investigation: join our Open Research Devroom at #FOSDEM2026. Call for proposal is open until December 1st. More info: research-fosdem.github.io
November 11, 2025 at 9:25 AM
📢 Calling all devs & users of #opensource tools for research & investigation: join our Open Research Devroom at #FOSDEM2026. Call for proposal is open until December 1st. More info: research-fosdem.github.io
We are ON 🔥 submit your talks for anything related to open research at our devroom at #FOSDEM2026 👇🏽
Great news! 🎉 Our Open Research devroom has been accepted for another year at @fosdem.org CfP is now OPEN. Go to our website to see how you can submit a talk on anything research: research-fosdem.github.io
🗓️ Sunday 1st February
📍 Brussels, Belgium
Looking forward to seeing you all at #FOSDEM2026 👩🏽💻
🗓️ Sunday 1st February
📍 Brussels, Belgium
Looking forward to seeing you all at #FOSDEM2026 👩🏽💻
a cartoon character says good news in front of a futurama sign
ALT: a cartoon character says good news in front of a futurama sign
media.tenor.com
November 10, 2025 at 7:47 PM
We are ON 🔥 submit your talks for anything related to open research at our devroom at #FOSDEM2026 👇🏽
Reposted by Violeta
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee
tl;dr: joint optimization of motion mask and scene reconstruction
arxiv.org/abs/2511.05229
Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee
tl;dr: joint optimization of motion mask and scene reconstruction
arxiv.org/abs/2511.05229
November 10, 2025 at 2:39 PM
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee
tl;dr: joint optimization of motion mask and scene reconstruction
arxiv.org/abs/2511.05229
Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee
tl;dr: joint optimization of motion mask and scene reconstruction
arxiv.org/abs/2511.05229
Reposted by Violeta
I have created this repo github.com/crp94/geospa... for easy, scalable, and flexible use of geospatial embeddings, currently supporting GeoCLIP and SatCLIP (more are coming!)
Not many new functionalities, it's just a simple wrapper that I created for my own convenience.
Not many new functionalities, it's just a simple wrapper that I created for my own convenience.
November 7, 2025 at 3:47 PM
I have created this repo github.com/crp94/geospa... for easy, scalable, and flexible use of geospatial embeddings, currently supporting GeoCLIP and SatCLIP (more are coming!)
Not many new functionalities, it's just a simple wrapper that I created for my own convenience.
Not many new functionalities, it's just a simple wrapper that I created for my own convenience.
Reposted by Violeta
🏆 Nominations to #CVMP2025 awards are still open in the following categories:
🧑💻 Research Impact
👥 Collaboration
📽️ Technology Impact
👉 More information to apply: www.cvmp-conference.org/2025/awards/
Please, share widely! And if you know anyone who could be interested, encourage them to apply!
🧑💻 Research Impact
👥 Collaboration
📽️ Technology Impact
👉 More information to apply: www.cvmp-conference.org/2025/awards/
Please, share widely! And if you know anyone who could be interested, encourage them to apply!
a woman is holding a small trophy that says " the assistant "
ALT: a woman is holding a small trophy that says " the assistant "
media.tenor.com
November 4, 2025 at 5:58 PM
🏆 Nominations to #CVMP2025 awards are still open in the following categories:
🧑💻 Research Impact
👥 Collaboration
📽️ Technology Impact
👉 More information to apply: www.cvmp-conference.org/2025/awards/
Please, share widely! And if you know anyone who could be interested, encourage them to apply!
🧑💻 Research Impact
👥 Collaboration
📽️ Technology Impact
👉 More information to apply: www.cvmp-conference.org/2025/awards/
Please, share widely! And if you know anyone who could be interested, encourage them to apply!
Reposted by Violeta
Great overview of the workshops and tutorials.
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
November 3, 2025 at 1:06 PM
Great overview of the workshops and tutorials.
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
My favorites:
1) CAD representation
2) synthetic data to help city-scale reconstruction
3) trends in 3D vision
4) visual chain-of-thoughts?
Reposted by Violeta
It's Halloween. So here's a story about the horror of replacing your developers with AI:
accu.org/journals/ove...
accu.org/journals/ove...
Judgment Day
What if AI takes your job? Teedy Deigh finds out.
accu.org
October 31, 2025 at 7:27 AM
It's Halloween. So here's a story about the horror of replacing your developers with AI:
accu.org/journals/ove...
accu.org/journals/ove...
Reposted by Violeta
Excited to announce our #EGU26 session “Machine learning & hybrid modelling for carbon cycle science, monitoring & carbon market policy”! 🌱
📅 Abstracts due 15 Jan 2026, 13:00 CET
🔗 meetingorganizer.copernicus.org/EGU26/sessio...
#ClimateScience #AI #CarbonCycle
📅 Abstracts due 15 Jan 2026, 13:00 CET
🔗 meetingorganizer.copernicus.org/EGU26/sessio...
#ClimateScience #AI #CarbonCycle
meetingorganizer.copernicus.org
October 31, 2025 at 10:59 AM
Excited to announce our #EGU26 session “Machine learning & hybrid modelling for carbon cycle science, monitoring & carbon market policy”! 🌱
📅 Abstracts due 15 Jan 2026, 13:00 CET
🔗 meetingorganizer.copernicus.org/EGU26/sessio...
#ClimateScience #AI #CarbonCycle
📅 Abstracts due 15 Jan 2026, 13:00 CET
🔗 meetingorganizer.copernicus.org/EGU26/sessio...
#ClimateScience #AI #CarbonCycle
Reposted by Violeta
The Impact and Outlook of 3D Gaussian Splatting
Bernhard Kerbl
tl;dr: in title
arxiv.org/abs/2510.26694
Bernhard Kerbl
tl;dr: in title
arxiv.org/abs/2510.26694
October 31, 2025 at 8:36 AM
The Impact and Outlook of 3D Gaussian Splatting
Bernhard Kerbl
tl;dr: in title
arxiv.org/abs/2510.26694
Bernhard Kerbl
tl;dr: in title
arxiv.org/abs/2510.26694
Yesss, see you there 🤗 and this year the networking dinner is back! 🎉🎉
Great news everyone 🎉
Early bird tickets are now on sale until the 15th of Nov to attend #CVMP2025 the Conference on Visual Media Production at #BFISouthbank 📽️ London this 3-4 of Dec
🎟️ Get your cheaper conference & networking dinner tickets here: www.cvmp-conference.org/2025/registr...
Early bird tickets are now on sale until the 15th of Nov to attend #CVMP2025 the Conference on Visual Media Production at #BFISouthbank 📽️ London this 3-4 of Dec
🎟️ Get your cheaper conference & networking dinner tickets here: www.cvmp-conference.org/2025/registr...
a cartoon character is talking on a telephone while wearing glasses
ALT: a cartoon character is talking on a telephone while wearing glasses
media.tenor.com
October 17, 2025 at 4:54 PM
Yesss, see you there 🤗 and this year the networking dinner is back! 🎉🎉
Reposted by Violeta
💩Thames Water's creditors are trying to strike a deal with Ofwat that could let them off complying with pollution rules until 2040.
There's a better way than their dirty tricks!
Public ownership - because we should have a say in how our water is run.
There's a better way than their dirty tricks!
Public ownership - because we should have a say in how our water is run.
October 10, 2025 at 8:28 AM
💩Thames Water's creditors are trying to strike a deal with Ofwat that could let them off complying with pollution rules until 2040.
There's a better way than their dirty tricks!
Public ownership - because we should have a say in how our water is run.
There's a better way than their dirty tricks!
Public ownership - because we should have a say in how our water is run.
Reposted by Violeta
Textured Gaussians for Enhanced 3D Scene Appearance Modeling
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, @jbhuang0604.bsky.social, Johannes Kopf, Gordon Wetzstein, Changil Kim
tl;dr: RGBA texture maps->Gaussians
arxiv.org/abs/2411.18625
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, @jbhuang0604.bsky.social, Johannes Kopf, Gordon Wetzstein, Changil Kim
tl;dr: RGBA texture maps->Gaussians
arxiv.org/abs/2411.18625
October 7, 2025 at 11:10 AM
Textured Gaussians for Enhanced 3D Scene Appearance Modeling
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, @jbhuang0604.bsky.social, Johannes Kopf, Gordon Wetzstein, Changil Kim
tl;dr: RGBA texture maps->Gaussians
arxiv.org/abs/2411.18625
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, @jbhuang0604.bsky.social, Johannes Kopf, Gordon Wetzstein, Changil Kim
tl;dr: RGBA texture maps->Gaussians
arxiv.org/abs/2411.18625
Reposted by Violeta
Proxy-GS: Efficient 3D Gaussian Splatting via Proxy Mesh
Yuanyuan Gao, Yuning Gong, Yifei Liu, Li Jingfeng, Zhihang Zhong, Dingwen Zhang, Yanci Zhang, @danxuhk.bsky.social, Xiao Sun
tl;dr: bridge hardware rasterization with a PyTorch-based proxy renderer
arxiv.org/abs/2509.24421
Yuanyuan Gao, Yuning Gong, Yifei Liu, Li Jingfeng, Zhihang Zhong, Dingwen Zhang, Yanci Zhang, @danxuhk.bsky.social, Xiao Sun
tl;dr: bridge hardware rasterization with a PyTorch-based proxy renderer
arxiv.org/abs/2509.24421
September 30, 2025 at 1:44 PM
Proxy-GS: Efficient 3D Gaussian Splatting via Proxy Mesh
Yuanyuan Gao, Yuning Gong, Yifei Liu, Li Jingfeng, Zhihang Zhong, Dingwen Zhang, Yanci Zhang, @danxuhk.bsky.social, Xiao Sun
tl;dr: bridge hardware rasterization with a PyTorch-based proxy renderer
arxiv.org/abs/2509.24421
Yuanyuan Gao, Yuning Gong, Yifei Liu, Li Jingfeng, Zhihang Zhong, Dingwen Zhang, Yanci Zhang, @danxuhk.bsky.social, Xiao Sun
tl;dr: bridge hardware rasterization with a PyTorch-based proxy renderer
arxiv.org/abs/2509.24421
Reposted by Violeta
DWGS: Enhancing Sparse-View Gaussian Splatting with Hybrid-Loss Depth Estimation and Bidirectional Warping
Yu Ma, Guoliang Wei, Yue Cheng
tl;dr: GIM-DKM+Depth Pro+bidirectional warp-based virtual training views+depth difference mask+SCGaussian
arxiv.org/abs/2509.24893
Yu Ma, Guoliang Wei, Yue Cheng
tl;dr: GIM-DKM+Depth Pro+bidirectional warp-based virtual training views+depth difference mask+SCGaussian
arxiv.org/abs/2509.24893
September 30, 2025 at 1:43 PM
DWGS: Enhancing Sparse-View Gaussian Splatting with Hybrid-Loss Depth Estimation and Bidirectional Warping
Yu Ma, Guoliang Wei, Yue Cheng
tl;dr: GIM-DKM+Depth Pro+bidirectional warp-based virtual training views+depth difference mask+SCGaussian
arxiv.org/abs/2509.24893
Yu Ma, Guoliang Wei, Yue Cheng
tl;dr: GIM-DKM+Depth Pro+bidirectional warp-based virtual training views+depth difference mask+SCGaussian
arxiv.org/abs/2509.24893
Reposted by Violeta
New! Cassetteboy vs Keir Starmer.
This took absolutely ages, so if you'd like to buy us a coffee at ko-fi.com/cassetteboy we'd really appreciate it. Thanks!
This took absolutely ages, so if you'd like to buy us a coffee at ko-fi.com/cassetteboy we'd really appreciate it. Thanks!
September 30, 2025 at 10:55 AM
New! Cassetteboy vs Keir Starmer.
This took absolutely ages, so if you'd like to buy us a coffee at ko-fi.com/cassetteboy we'd really appreciate it. Thanks!
This took absolutely ages, so if you'd like to buy us a coffee at ko-fi.com/cassetteboy we'd really appreciate it. Thanks!
Are public institutions trying to gaslight us into thinking that Microsoft software products are good quality? I've been trying for the last 10min to get some nested bullet points working on powerpoint... I think it's impossible? Is there anything more basic than this? I am baffled
September 30, 2025 at 10:58 AM
Are public institutions trying to gaslight us into thinking that Microsoft software products are good quality? I've been trying for the last 10min to get some nested bullet points working on powerpoint... I think it's impossible? Is there anything more basic than this? I am baffled
Reposted by Violeta
Para las sabandijas que solo queréis cosas gratis: voy a sortear algunas entraditas (también vale para las fechas por España). Solamente tenéis que rebluitear esta publicación y el lunes anunciaré los 5 ganadores con alguna app fraudulenta o directamente a dedo. Me da igual. Aguante Maxwell Cremona.
September 25, 2025 at 8:34 AM
Para las sabandijas que solo queréis cosas gratis: voy a sortear algunas entraditas (también vale para las fechas por España). Solamente tenéis que rebluitear esta publicación y el lunes anunciaré los 5 ganadores con alguna app fraudulenta o directamente a dedo. Me da igual. Aguante Maxwell Cremona.
Reposted by Violeta
Neural-MMGS: Multi-modal Neural Gaussian Splats for Large-Scale Scene Reconstruction
Sitian Shen, Georgi Pramatarov, @taoyifu.bsky.social, Daniele De Martini
tl;dr: RGB & LiDAR & semantics->GS embeddings
arxiv.org/abs/2509.17762
Sitian Shen, Georgi Pramatarov, @taoyifu.bsky.social, Daniele De Martini
tl;dr: RGB & LiDAR & semantics->GS embeddings
arxiv.org/abs/2509.17762
September 23, 2025 at 7:14 PM
Neural-MMGS: Multi-modal Neural Gaussian Splats for Large-Scale Scene Reconstruction
Sitian Shen, Georgi Pramatarov, @taoyifu.bsky.social, Daniele De Martini
tl;dr: RGB & LiDAR & semantics->GS embeddings
arxiv.org/abs/2509.17762
Sitian Shen, Georgi Pramatarov, @taoyifu.bsky.social, Daniele De Martini
tl;dr: RGB & LiDAR & semantics->GS embeddings
arxiv.org/abs/2509.17762
Reposted by Violeta
SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
Ranran Huang, Krystian Mikolajczyk
tl;dr: masked attention in decoder->context–target separation within a single branch; SPFSplat for VGGT
arxiv.org/abs/2509.17246
Ranran Huang, Krystian Mikolajczyk
tl;dr: masked attention in decoder->context–target separation within a single branch; SPFSplat for VGGT
arxiv.org/abs/2509.17246
September 23, 2025 at 7:15 PM
SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
Ranran Huang, Krystian Mikolajczyk
tl;dr: masked attention in decoder->context–target separation within a single branch; SPFSplat for VGGT
arxiv.org/abs/2509.17246
Ranran Huang, Krystian Mikolajczyk
tl;dr: masked attention in decoder->context–target separation within a single branch; SPFSplat for VGGT
arxiv.org/abs/2509.17246
Reposted by Violeta
HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
Zipeng Wang, @danxuhk.bsky.social
tl;dr: grid-based neural fields->low-frequency variations; explicit Gaussians->high-frequency details; separate geometry&view-dependent effects
arxiv.org/abs/2509.17083
Zipeng Wang, @danxuhk.bsky.social
tl;dr: grid-based neural fields->low-frequency variations; explicit Gaussians->high-frequency details; separate geometry&view-dependent effects
arxiv.org/abs/2509.17083
September 23, 2025 at 7:16 PM
HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
Zipeng Wang, @danxuhk.bsky.social
tl;dr: grid-based neural fields->low-frequency variations; explicit Gaussians->high-frequency details; separate geometry&view-dependent effects
arxiv.org/abs/2509.17083
Zipeng Wang, @danxuhk.bsky.social
tl;dr: grid-based neural fields->low-frequency variations; explicit Gaussians->high-frequency details; separate geometry&view-dependent effects
arxiv.org/abs/2509.17083
Reposted by Violeta
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
Shi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li, @martin-r-oswald.bsky.social
tl;dr: Splat-SLAM+SAM2->tracking; Motion Scaffolds+GS->dynamic
arxiv.org/abs/2509.17864
Shi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li, @martin-r-oswald.bsky.social
tl;dr: Splat-SLAM+SAM2->tracking; Motion Scaffolds+GS->dynamic
arxiv.org/abs/2509.17864
September 23, 2025 at 7:12 PM
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
Shi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li, @martin-r-oswald.bsky.social
tl;dr: Splat-SLAM+SAM2->tracking; Motion Scaffolds+GS->dynamic
arxiv.org/abs/2509.17864
Shi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li, @martin-r-oswald.bsky.social
tl;dr: Splat-SLAM+SAM2->tracking; Motion Scaffolds+GS->dynamic
arxiv.org/abs/2509.17864
Reposted by Violeta
GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Jiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu
tl;dr: monocular depth+voxel uncertainty+voxel pruning
arxiv.org/abs/2509.18090
Jiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu
tl;dr: monocular depth+voxel uncertainty+voxel pruning
arxiv.org/abs/2509.18090
September 23, 2025 at 7:11 PM
GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Jiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu
tl;dr: monocular depth+voxel uncertainty+voxel pruning
arxiv.org/abs/2509.18090
Jiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu
tl;dr: monocular depth+voxel uncertainty+voxel pruning
arxiv.org/abs/2509.18090
Reposted by Violeta
UN says the genocide in Gaza won't stop as it's profitable. Palestine is a training field to test weapons & surveillance tech that are now sold worldwide.
Those making billions?
Palantir, Lockheed Martin, Alphabet, Amazon, IBM, Caterpillar, Microsoft, MIT, Blackrock, insurers, real estate firms.
Those making billions?
Palantir, Lockheed Martin, Alphabet, Amazon, IBM, Caterpillar, Microsoft, MIT, Blackrock, insurers, real estate firms.
September 23, 2025 at 8:51 AM
UN says the genocide in Gaza won't stop as it's profitable. Palestine is a training field to test weapons & surveillance tech that are now sold worldwide.
Those making billions?
Palantir, Lockheed Martin, Alphabet, Amazon, IBM, Caterpillar, Microsoft, MIT, Blackrock, insurers, real estate firms.
Those making billions?
Palantir, Lockheed Martin, Alphabet, Amazon, IBM, Caterpillar, Microsoft, MIT, Blackrock, insurers, real estate firms.