Tootfinder

heise | Supermodel: Die schönsten Spielautomaten-Klassiker der 90er im Emulator spielen
Traumhafte Grafik, sofortiger Spaß: So emulieren Sie Model-3-Klassiker wie Daytona USA 2 oder Virtua Fighter 3 heute noch ansehnlich.

🇺🇦 Auf radioeins läuft...
Sepalot:
🎵 My Own Way
#NowPlaying #Sepalot
https://sepalot.bandcamp.com/track/my-own-way
https://open.spotify.com/track/1fZWCdpLnT98Lf5DeGkMSB

ReSplat: Learning Recurrent Gaussian Splats
Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys
https://arxiv.org/abs/2510.08575 https://arxiv.org/pdf…

ReSplat: Learning Recurrent Gaussian Splats
While feed-forward Gaussian splatting models provide computational efficiency and effectively handle sparse input settings, their performance is fundamentally limited by the reliance on a single forward pass during inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients. Our key insight is that the Gaussian splatting rendering error serves as a rich feedback signal, guiding the recurrent networ…

A list of sci-fi movies ordered by the year they were set in (not when they were made). Those years that are now in the past are marked in blue!
#SciFi https://rheinneckar.social/@splitmind/

The US Navy and Palantir announce ShipOS, saying the software will speed up shipbuilding and improve supply chain visibility; the deal is valued at $448M (Colin Demarest/Axios)
https://www.axios.com/2025/12/09/navy-phelan-palantir-karp-shipos

Navy unveils "ShipOS" with Palantir to speed up shipbuilding
"This is, essentially, doing predictive work on supply chain management," CEO Alex Karp told reporters.

Splat the Net: Radiance Fields with Splattable Neural Primitives
Xilong Zhou, Bao-Huy Nguyen, Lo\"ic Magne, Vladislav Golyanik, Thomas Leimk\"uhler, Christian Theobalt
https://arxiv.org/abs/2510.08491

Splat the Net: Radiance Fields with Splattable Neural Primitives
Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, whereas primitive-based methods such as 3D Gaussian Splatting offer real-time efficiency through splatting, yet at the expense of representational power. Inspired by advances in both these directions, we introduce splattable neural primitives, a new volumetric representation that…

🇺🇦 #NowPlaying on BBCRadio3's #LateJunction
Split Apex:
🎵 Cast in Light
#SplitApex
Please 🔁 BOOST to share what you like
- your followers don't see if you ⭐ favourite a post

#NowPlaying the new Shellyduvall/Misanthropy split. Been noticing a lot of industrial and cyber being mixed in with the grind and noise and metal lately and I'm here for it. This weird, plodding shit rips.
https://she…

D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
Meixi Song, Xin Lin, Dizhe Zhang, Haodong Li, Xiangtai Li, Bo Du, Lu Qi
https://arxiv.org/abs/2510.08566

D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
Recent advances in 3D Gaussian Splatting (3DGS) enable real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations. However, performance degradation and instability remain significant under sparse-view conditions. In this work, we identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage. To address these challenges, we propose…