[ICLR 2026] NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

LLM IS AS GOOD AS YOU ARE

[CVPR 2026 Highlight] Official STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction

practice made claude perfect

[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

[ICLR'26] YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting

[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

[ CVPR 2025 ] We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environments in a patch-by-patch and coarse-to-fine fashion.

Official repository for "SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE"

This repository contains the code for the paper - "Aligning Text, Images, and 3D Structure Token-by-Token" (CVPR 2026)

[ICCV2025] II-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting

4Deform: Neural Surface Deformation for Robust Shape Interpolation

Easily display interactive 3D models on the web and in AR!

[ICLR 2026 oral] Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

PaperBanana: Automating Academic Illustration For AI Scientists

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

Official repo for "Generative Point Tracking with Flow Matching".

Advancing Open-source World Models

GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting

[CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

🌐 3D and 4D World Modeling: A Survey

SynCity: Training-Free Generation of 3D Worlds

Code of WinT3R: Window-Based Streaming Rrconstruction With Camera Token Pool

[3DV 2026 Oral] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

[ICCV 2025] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

[CVPR'25] 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians