Jan

Researching 3D Reconstruction & Generation | PhD Student University of Tübingen @CG_Tuebingen & @MPI_IS | Previously @saysomapp

[Computer Graphics Tübingen @CG_Tuebingen]

Computer Games Course 25/26
Topic: Tamed Growth

Rootfall 🌱 a cozy physics-based destruction game where you play as a climbing plant reclaiming abandoned human structures. Grow, plan your route, avoid fireflies, and collapse the world gently.
https://t.co/8IVOFLy44h

[Computer Graphics Tübingen @CG_Tuebingen]

Computer Games Course 25/26
Topic: Tamed Growth

Squidweird 🐙 a physics based 2D puzzle adventure where you swing a stranded squid back to the ocean. Master momentum, combine tentacles, avoid hazards, and find creative paths forward.
https://t.co/bX0UT2JjIU

[Computer Graphics Tübingen @CG_Tuebingen]

Computer Games Course 25/26
Topic: Tamed Growth

Sketch Blossom 🎨🌿 a turn based battle game where your drawings become your weapons. Sketch plants, fight, collect, and upgrade > better drawings hit harder. One mistake, and your plant is gone forever.
https://t.co/BL7QDEs8AQ

[Computer Graphics Tübingen @CG_Tuebingen]

Computer Games Course 25/26
Topic: Tamed Growth

ELIT 🤖🎮 a chaotic AI-powered party game where your prompts become playable 3D objects. Create, fight, and guess with friends in fast-paced rounds with proximity chat and wild interactions.
https://t.co/GoMegusHNA

[Computer Graphics Tübingen @CG_Tuebingen]

Computer Games Course 25/26
Topic: Tamed Growth

Still Asleep 🌌 a surreal puzzle runner where you build your own path through a collapsing dream. Harvest energy, place tiles, and chase your true self before the world disappears beneath you.
https://t.co/X8MwJijVp0

[Jan @JDihlmann]

Proud to announce that MatSpray has been accepted to CVPR 2026. We also released the code yesterday, in case you’re interested in building on it.

See you in Denver, Colorado!

[Jan @JDihlmann]

MatSpray: Fusing 2D Material World Knowledge on 3D Geometry

Super fast materials for every 3D Gaussian Splatting scene from swappable foundation models.

Work together with Philipp Langsteiner @CleanupVessel94 from our @CG_Tuebingen

Links 👇

[Jan @JDihlmann]

Code: https://t.co/MxqVMxczqt
Weights: https://t.co/Yvhu9bTMz8

[Jan @JDihlmann]

ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination

Sparse Posed RGB -> Geometry + Materials + Illumination < 1s
https://t.co/t5YArOFPWK
https://t.co/6zI8KqQZIr

feat: @CG_Tuebingen @markb_boss @AjlEngelhardt @jampani_varun

[Jan @JDihlmann]

Pipeline: multi-view cross-conditioning -> shared triplane. Two paths: svBRDF materials + RENI++ environment lighting. Trained with differentiable MC + MIS (mixed-domain: synthetic PBR/RGB-only + real UCO3D).

[Jan @JDihlmann]

@humphrey_shi @chen940382 @CVPR @humphrey_shi Another question on this, perhaps something to add in the official instructions: Is this considered an officially published paper?

If we opt in, would it still be possible to submit the work to another venue, e.g., ECCV, or would that count as a double submission?

[Ryohei Sasaki@engineer @rsasaki0109]

3D-RE-GEN
3D Reconstruction of Indoor Scenes with a Generative Framework
https://t.co/xJQRiWLA3G
We propose single-image 3D scene reconstruction for producing complete, editable scenes from a single photograph. Our method reconstructs individual objects and the surrounding background as textured 3D assets, enabling coherent scene assembly from minimal input. We combine instance segmentation, context-aware generative inpainting, 2D-to-3D asset creation, and constrained optimization to recover physically plausible geometry, materials, and lighting. The resulting scenes preserve correct spatial relationships, lighting consistency, and material fidelity, making them suitable for production-ready workflows.

[Jan @JDihlmann]

@PhilipvN @AIatMeta We‘ll release code soon, maybe with a Demo. I‘ll keep you posted.

[Jan @JDihlmann]

3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework

from a single image to a complete, editable 3D scene with individual objects AND a reconstructed background - VFX ready.

New work from us @CG_Tuebingen together with my student Tobias Sautter.

Links 👇

[Jan @JDihlmann]

@PhilipvN This is single view right now, sure the VGGT prediction could be improved with MV. But the object gen models don’t allow for MV, if so this would def help … but one bottleneck is our inpainting, this is not easily MVable as it is happening in 2D space.

[Jan @JDihlmann]

Thanks for sharing @janusch_patas!

[MrNeRF @janusch_patas]

MatSpray: Fusing 2D Material World Knowledge on 3D Geometry

Contributions:
��� World Material Fusion: A plug-and-play pipeline that, to our knowledge, is the first to fuse swappable diffusion-based 2D PBR priors ("world material knowledge") with 3D Gaussian material optimization. It uses Gaussian ray tracing and PBR consistent supervision to obtain relightable assets.

• Neural Merger: A softmax neural merger that aggregates per-Gaussian, multi-view material estimates, suppresses baked-in lighting, and enforces cross-view consistency while stabilizing joint environment map optimization.

• Faster Reconstruction: A simple projection and optimization scheme that reconstructs high-quality relightable 3D materials with 3.5× less per-scene optimization time than IRGS [9].

[Jan @JDihlmann]

2D diffusion models predict great PBR materials (base color, roughness, metallic) but they're inconsistent across views. MatSpray uses Gaussian ray tracing to lift these predictions into 3D, then our Neural Merger enforces multi-view consistency while preserving diffusion priors.

[Jan @JDihlmann]

MatSpray: Fusing 2D Material World Knowledge on 3D Geometry

Super fast materials for every 3D Gaussian Splatting scene from swappable foundation models.

Work together with Philipp Langsteiner @CleanupVessel94 from our @CG_Tuebingen

Links 👇

[Jan @JDihlmann]

MatSpray outperforms state-of-the-art inverse rendering methods in relighting quality, especially for specular and metallic objects.

Plus, it's 3.5× faster than IRGS, reconstructing high-quality relightable materials in ~25 minutes per scene.

[Jan @JDihlmann]

Messed up the website link it is
https://t.co/pF48jN2dYI

[Jan @JDihlmann]

Learn more about FrameDiffuser on our website and on Arxiv and feel free to waitlist the code.
🌐 https://t.co/FxD7v9iHvu
📃 https://t.co/PO3slt0685
💾 https://t.co/N1QogECtgI

(Explore the Thread to see how we even beat SAM3D)