Christian Richardt
@c_richardt
Followers
2K
Following
13K
Media
117
Statuses
2K
Research Scientist at @RealityLabs. Working on novel-view synthesis etc. Previously @UniofBath, #IVCI @Saar_Uni, #MPI_Informatik, @Inria, @Cambridge_Uni.
Zurich, Switzerland
Joined January 2012
RT @amritamaz: The recordings from the #CVPR2025 tutorial "Volumetric Video in the Real World" are now available!
0
14
0
RT @_ilya_c: Recording of the workshop is now online, big thanks to all the organizers and everyone who attended both in person and online!….
0
7
0
RT @alexcarliera: 🔥 Very cool to bring paintings to life with Kling 2.1 while visiting the @NationalGallery in London 🇬🇧 . Made with @Photo….
0
7
0
RT @ZhiHaoLin16: Excited to share our work at #CVPR2025!.👁️IRIS estimates accurate surface material, spatially-varying HDR lighting, and ca….
0
10
0
RT @_TianyeLi: Join our #CVPR2025 Tutorial on Volumetric Video in the Real World on 6/11! With amazing speakers:.@holynski_ @c_richardt @i….
0
8
0
RT @zhenjun_zhao: Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency. Hyunho Ha, @leixiao08, @c_richardt, @thun….
0
8
0
RT @zhenjun_zhao: Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields. Runfeng Li, Mikhail Okunev,….
0
6
0
RT @janusch_patas: Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields. Problem:.In continuous-wave….
0
11
0
💙 Acknowledgments.AVG in collaboration with Peter Kontschieder's team at @Meta @RealityLabs. 👥 Stefano Esposito, @AnpeiC, @ChrisJReiser, Samuel Rota Bulò, Lorenzo Porzi, @K_S_Schwarz, Christian Richardt, @MZollhoefer, Peter Kontschieder, Andreas Geiger.
0
0
1
🎮 Try it yourself!.Our WebGL viewer loads the baked meshes & textures right in the browser—runs on iPhone, Android, and Intel UHD laptops. 🎮
1
1
3
📱 Evaluation.Device : Samsung A52s (2021) − 720p.• 65 FPS (3‑Mesh) → 35 FPS (9‑Mesh).• Beats 3DGS (~ 8 FPS) and MobileNeRF (~ 24 FPS) image quality: 34.5 dB PSNR (7‑Mesh) — higher than MobileNeRF (29.3 dB) and close to 3DGS (35.4 dB).
1
0
1
🔧 How it works.We learn a fixed number of SDF “shells”. 1️⃣ Reconstruct implicit semi‑transparent adaptively-spaced shells. 2️⃣ Bake each shell into a tiny mesh + SH texture. The GPU then just rasterizes and alpha‑blends in a fixed order—no ray‑marching, no depth sort.
1
0
1
🚀 Efficiency and quality.• Surface rendering → fast but miss fuzz.• Volume rendering → high capacity but inefficient.• We skip sorting & empty space and use only 3–9 samples by rasterizing smooth, lightweight meshes → quality like 3DGS, much higher rendering efficiency
1
0
1
📢 New paper @CVPR!.Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair + fur. It’s fast, looks great, and runs in real time even on budget phones. 🔗 📄
2
14
77
RT @TobiasFischer11: 1/3 Introducing FlowR 🌸: Flowing from Sparse to Dense 3D Reconstructions. We learn a direct mapping between incorrect….
0
40
0
RT @K_S_Schwarz: Ever wondered how to integrate 3DGS into a pretrained video diffusion model? Check out our new approach, Generative Gauss….
0
16
0