A::B Prompting Challenge: $10k to prove me wrong! # CHALLENGE Develop an AI prompt that solves random 12-token instances of the A::B problem (defined in the quoted tweet), with 90%+ success rate. # RULES 1. The AI will be given a random instance, inside a <problem/> tag. 2.

DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping A method for large-scale 3D scene reconstruction from sparse 3D LiDAR scans. Project: artonson.github.io/publications/2… Vid: youtu.be/WC-pcaf94N4 Text: arxiv.org/pdf/2403.17550…

#CVPR2024 has now come to an end. It was a great conference and I am glad I could be part of it, presenting our work Tim Weyrich, find me on Bsky on Anomaly Localization and Clustering. PRIME-ITN

It was a wonderful experience being a part of this project. Generating multi-view 2D and then reconstructing 3D provides a scalable and a modular way for text-to-3D generation.

📢 Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View 🌐 Project page: andreeadogaru.github.io/Gen3DSR 📄 Paper: arxiv.org/abs/2404.03421 👩‍💻 Code: github.com/AndreeaDogaru/… Compositional 3D reconstruction of complex scenes with unprecedented quality🧵

Our poster Tim Weyrich, find me on Bsky is still up at #SIGGRAPH2024, you are welcome to come by and check it out if you didn't have the chance yet!

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion discuss: huggingface.co/papers/2408.03… We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry,

Diffusion Models Are Real-Time Game Engines abs: arxiv.org/abs/2408.14837 project page: gamengen.github.io Google presents GameNGen, the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories

Great work by the Penrose team building Bloom: a lightweight way to make interactive diagrams: penrose.cs.cmu.edu/blog/bloom All coordinates are automatically figured out by the Penrose layout engine, and diagram specifications can be re-used for different content (like HTML/CSS).

Matérn Kernels for Tunable Implicit Surface Reconstruction Paper: arxiv.org/abs/2409.15466 We use Matérn kernels for 3D surface reconstruction, acting as a drop-in replacement of the arc-cosine kernel in frameworks such as Neural Splines & Neural Kernel Fields. Code on GitHub!

We dropped a great paper today! Frustrated by some of the limits of Gaussian Splatting, we developed EVER: a drop-in 3DGS replacement that raytraces constant-density ellipsoids. This gives much higher image quality and flexibility than 3DGS while retaining real-time speeds.

❓️Want to fuse RGB-D 📷 with high-resolution radars 📡 ? ➡️ Check out our paper "Automatic Spatial Calibration of Near-Field MIMO Radar With Respect to Optical Depth Sensors" 🤖 Accepted at #iros 2024 🌐: vwirth.github.io/nfcalib 📃: arxiv.org/abs/2403.10981

Happy to share our paper: "Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering" TL;DR: Monocular depth estimate➡️ SfM absolute depth scale➡️ coarse and local mesh optimization for accurate depths 📖: lorafib.github.io/ref_depth 📜: arxiv.org/abs/2410.03861

Following over 1.5 years of hard work (w/Nicolas Roussel& Rami Tabbara), we just released a brand-new version of Dr.Jit (v1.0), my lab's differentiable rendering compiler along with an updated Mitsuba (v3.6). The list of changes is insanely long—here is what we're most excited about🧵

GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction Contributions: • We introduce an efficient framework for high-quality surface reconstruction using 3D Gaussians. • We integrate the traditional MVS algorithm patch matching and normal priors within our

Meshtron High-Fidelity, Artist-Like 3D Mesh Generation at Scale from NVIDIA TL;DR: Autoregressive mesh generator based on the Hourglass architecture and using sliding window attention; point cloud to mesh; txt2mesh; mesh2mesh

ℏεsam Here is a simple prompt: """ As a math specialist, write a Manim program that explains the following problem with precision and engaging, easy-to-understand animations. <problem>{your problem}</problem> <solution>{you can also induce solution}</solution> """

Had a great experience presenting our work on 3D scene reconstruction from a single image with Bernhard Egger at #3DV2025 🇸🇬 andreeadogaru.github.io/Gen3DSR Reach out if you're interested in discussing our research or exploring international postdoc opportunities Cognitive Computer Vision Lab FAU Erlangen-Nbg

The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵arxiv.org/abs/2505.16993

Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.