Peter Kocsis
@Peter4AI
Followers
605
Following
249
Media
7
Statuses
251
PhD student at TUM, Visual Computing & Artificial Intelligence Group
Munich
Joined November 2021
RT @LukasHollein: 📢Code release for 3DGS-LM (#ICCV2025)📢. Gaussian-Splatting made faster by changing the underlying optimizer. It's compati….
0
24
0
RT @MattNiessner: ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH). We reconstruct ultra-high fidelity pho….
0
37
0
RT @MattNiessner: 📢 LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans🏠✨. -> converts RGB-D scans into compact, realistic….
0
65
0
RT @angelaqdai: Check out our #ICCV2025 work on functional 3d scan editing, learning to optimize, multi-level 3d captioning, interactive me….
0
25
0
Amazing in-the-wild video relighting results! I like the quality of the cast shadows, showing that current diffusion models have understanding about light propagation.
🚀 We just open-sourced Cosmos DiffusionRenderer!. This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! .🔗
1
0
5
RT @ErkocZiya: Presenting PrEditor3D at #CVPR2025 📢📢. If you'd like to learn more about our work and discuss 3D generation/editing, come vi….
0
10
0
RT @janusch_patas: Check out the EnvGS code. Now open-source! . Recently added: high-quality real-time GUI rendering to view base color, re….
0
19
0
RT @MattNiessner: 📢BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading. We propose a hybrid neural shading scheme for crea….
0
76
0
RT @MattNiessner: 📢Code Release of Pixel3DMM 📢. Looking for a robust and accurate face tracker? . Our state-of-the-art tracker handles cha….
0
98
0
RT @MattNiessner: 📢PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors📢. We propose a new optimization to up-sample textures of….
0
37
0
RT @MattNiessner: 📢📢𝐁𝐈𝐆 𝐍𝐄𝐖𝐒: 𝐒𝐮𝐩𝐞𝐫 𝐞𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐒𝐩𝐀𝐈𝐭𝐢𝐚𝐥 𝐀𝐈 📢📢. We’re building Spatial Foundation Models — a new paradigm of genera….
0
71
0
RT @angelaqdai: 📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization. @liuyuehcheng learns 2DGS initialization,….
0
57
0
RT @MattNiessner: 📢GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans📢. We present a novel method to reconstruct hair strands….
0
43
0
RT @MattNiessner: 📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢. -> highly accurate face reconstructio….
0
126
0
RT @MattNiessner: 📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢. We use octahedra or tetrahedra as explicit as vo….
0
34
0
RT @angelaqdai: 📢ScanEdit: Hierarchically-Guided Functional 3D Scan Editing. Edit complex, real-world 3D scans with text -- @ElBoudjogh2400….
0
39
0
RT @MattNiessner: 📢 SHeaP: Self-Supervised Head Predictor Learned via 2D Gaussians 📢. Given a single input image, we predict accurate 3D he….
0
60
0
Happy to share our latest work: IntrinsiX 🥳. We generate intrinsic components directly from text! Using SDS, our model can generate full room-scale PBR textures, ready for photo-realistic rendering. Big shout-out to @LukasHollein and @MattNiessner!.
📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢. From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train
0
23
113
RT @MattNiessner: 📢Announcing our 3D head avatar benchmark📢. Two tasks with hidden test sets:.- Dynamic Novel View Synthesis on Heads.- Mon….
0
37
0