#ICCV2023 We curated a large-scale, comprehensive, and high-quality synthetic dataset MatrixCity for city-scale neural rendering based on the UE5 City Sample. #ICCV2025 -Project: city-super.github.io/matrixcity/ -Paper: arxiv.org/abs/2309.16553

Checkout our work tomorrow morning (10/4 at 10:30AM-12:30PM) at Room "Foyer Sud"-101. Looking forward to share inspirations and thoughts on city-scale scenes modeling.

We have released the MatrixCityPlugin, render sequences, config and related scripts (github.com/city-super/Mat…). - collect large-scale and high-quality city data. - control lighting, fog, human and car crowds. - obtain depth, normal, decomposed BRDF materials.

Wanna evaluate your own "dreamer" but facing the challenge of expensive user studies? Dive into our newest work for #CVPR2024: leveraging GPT-4V for a concise, versatile, and human-aligned evaluation. Give it a shot!

Octree-GS Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for

check the code and demos at city-super.github.io/octree-gs/ 🚀 :)

Excited to release 🚀NeRF-XL🚀, a principled method to distribute your NeRF's parameters to multiple GPUs! research.nvidia.com/labs/toronto-a… It is heuristics-free and mathematically equiv. with training your NeRF on a single (large) GPU. Let's scale it up!🌎

Imagine we could capture stunning scenes with NeRF and enhance them like photos? It's easy if you try our #SIGGRAPH2024 work. We introduce a method to "Lightroom" 3D scenes. Plus, it enables NeRF training on images with varying exposure. Project: bilarfpro.github.io (1/3)

Want to generate camera controllable human videos like a real movie clip? Try our HumanVid dataset and a baseline model combined by AnimateAnyone and CameraCtrl. Project Page: humanvid.github.io Paper: arxiv.org/pdf/2407.17438 Data and code coming soon.

We are excited to introduce LayerPano3D, a novel framework to generate full-view, explorable panoramic 3D scene from a single text prompt! More examples are in our project page. ✨Project: ys-imtech.github.io/projects/Layer… ✨Paper: arxiv.org/abs/2408.13252 ✨Code: github.com/YS-IMTech/Laye…

🚀Excited to introduce 𝗜𝗺𝗮𝗴𝗶𝗻𝗲𝟯𝟲𝟬, the 1st framework that lifts standard videos into 360 videos with rich and structured motion, unlocking dynamic scene experience from full 360 degrees. 🎥🌍 - Webpage (w/ VR): ys-imtech.github.io/projects/Imagi… - Arxiv: arxiv.org/abs/2412.03552

Introducing Doppelgangers++! 🚀 An enhanced pairwise image classifier that tackles visual aliasing (doppelgangers) to improve 3D reconstruction accuracy across diverse, real-world scenes. 🌍✨ 🔗Project page: bit.ly/3VAPMJc. Code is also available.

[1/3] Want to capture a fantastic HDR image by 2 simple shots with your cellphone? Try UltraFusion HDR. It takes two images with exposure differences up to 9 stops, and it robustly generates HDR output. Try your own captured images (supporting 4Kx3K): huggingface.co/spaces/iimmort…

We propose Long Context Tuning (LCT) for scene-level video generation to bridge the gap between current single-shot generation and real-world narrative video productions. Homepage: guoyww.github.io/projects/long-… Report: arxiv.org/abs/2503.10589

Video generation model could now generate multi-person dialogue videos or talking videos with HOI, from text prompts and N pairs of {cropped reference images (e.g., head images), audio} without any lip post-processing. Paper: arxiv.org/abs/2506.09984 Demo: zhenzhiwang.github.io/interacthuman/